literature review ai

AI Literature Review Generator

Automated literature review creation tool.

• Academic Research: Create a literature review for your thesis, dissertation, or research paper.
• Professional Research: Conduct a literature review for a project, report, or proposal at work.
• Content Creation: Write a literature review for a blog post, article, or book.
• Personal Research: Conduct a literature review to deepen your understanding of a topic of interest.

New & Trending Tools

Text style transfer, one-page report writer, study buddy.

The best AI tools for research papers and academic research (Literature review, grants, PDFs and more)

As our collective understanding and application of artificial intelligence (AI) continues to evolve, so too does the realm of academic research. Some people are scared by it while others are openly embracing the change. 

Make no mistake, AI is here to stay!

Instead of tirelessly scrolling through hundreds of PDFs, a powerful AI tool comes to your rescue, summarizing key information in your research papers. Instead of manually combing through citations and conducting literature reviews, an AI research assistant proficiently handles these tasks.

These aren’t futuristic dreams, but today’s reality. Welcome to the transformative world of AI-powered research tools!

The influence of AI in scientific and academic research is an exciting development, opening the doors to more efficient, comprehensive, and rigorous exploration.

This blog post will dive deeper into these tools, providing a detailed review of how AI is revolutionizing academic research. We’ll look at the tools that can make your literature review process less tedious, your search for relevant papers more precise, and your overall research process more efficient and fruitful.

I know that I wish these were around during my time in academia. It can be quite confronting when trying to work out what ones you should and shouldn’t use. A new one seems to be coming out every day!

Here is everything you need to know about AI for academic research and the ones I have personally trialed on my Youtube channel.

Best ChatGPT interface – Chat with PDFs/websites and more

I get more out of ChatGPT with HeyGPT . It can do things that ChatGPT cannot which makes it really valuable for researchers.

Use your own OpenAI API key ( h e re ). No login required. Access ChatGPT anytime, including peak periods. Faster response time. Unlock advanced functionalities with HeyGPT Ultra for a one-time lifetime subscription

AI literature search and mapping – best AI tools for a literature review – elicit and more

Harnessing AI tools for literature reviews and mapping brings a new level of efficiency and precision to academic research. No longer do you have to spend hours looking in obscure research databases to find what you need!

AI-powered tools like Semantic Scholar and elicit.org use sophisticated search engines to quickly identify relevant papers.

They can mine key information from countless PDFs, drastically reducing research time. You can even search with semantic questions, rather than having to deal with key words etc.

With AI as your research assistant, you can navigate the vast sea of scientific research with ease, uncovering citations and focusing on academic writing. It’s a revolutionary way to take on literature reviews.

• Elicit –  https://elicit.org
• Supersymmetry.ai: https://www.supersymmetry.ai
• Semantic Scholar: https://www.semanticscholar.org
• Connected Papers –  https://www.connectedpapers.com/
• Research rabbit – https://www.researchrabbit.ai/
• Laser AI –  https://laser.ai/
• Litmaps –  https://www.litmaps.com
• Inciteful –  https://inciteful.xyz/
• Scite –  https://scite.ai/
• System –  https://www.system.com

If you like AI tools you may want to check out this article:

• How to get ChatGPT to write an essay [The prompts you need]

AI-powered research tools and AI for academic research

AI research tools, like Concensus, offer immense benefits in scientific research. Here are the general AI-powered tools for academic research. 

These AI-powered tools can efficiently summarize PDFs, extract key information, and perform AI-powered searches, and much more. Some are even working towards adding your own data base of files to ask questions from. 

Tools like scite even analyze citations in depth, while AI models like ChatGPT elicit new perspectives.

The result? The research process, previously a grueling endeavor, becomes significantly streamlined, offering you time for deeper exploration and understanding. Say goodbye to traditional struggles, and hello to your new AI research assistant!

• Bit AI –  https://bit.ai/
• Consensus –  https://consensus.app/
• Exper AI –  https://www.experai.com/
• Hey Science (in development) –  https://www.heyscience.ai/
• Iris AI –  https://iris.ai/
• PapersGPT (currently in development) –  https://jessezhang.org/llmdemo
• Research Buddy –  https://researchbuddy.app/
• Mirror Think – https://mirrorthink.ai

AI for reading peer-reviewed papers easily

Using AI tools like Explain paper and Humata can significantly enhance your engagement with peer-reviewed papers. I always used to skip over the details of the papers because I had reached saturation point with the information coming in. 

These AI-powered research tools provide succinct summaries, saving you from sifting through extensive PDFs – no more boring nights trying to figure out which papers are the most important ones for you to read!

They not only facilitate efficient literature reviews by presenting key information, but also find overlooked insights.

With AI, deciphering complex citations and accelerating research has never been easier.

• Open Read –  https://www.openread.academy
• Chat PDF – https://www.chatpdf.com
• Explain Paper – https://www.explainpaper.com
• Humata – https://www.humata.ai/
• Lateral AI –  https://www.lateral.io/
• Paper Brain –  https://www.paperbrain.study/
• Scholarcy – https://www.scholarcy.com/
• SciSpace Copilot –  https://typeset.io/
• Unriddle – https://www.unriddle.ai/
• Sharly.ai – https://www.sharly.ai/

AI for scientific writing and research papers

In the ever-evolving realm of academic research, AI tools are increasingly taking center stage.

Enter Paper Wizard, Jenny.AI, and Wisio – these groundbreaking platforms are set to revolutionize the way we approach scientific writing.

Together, these AI tools are pioneering a new era of efficient, streamlined scientific writing.

• Paper Wizard –  https://paperwizard.ai/
• Jenny.AI https://jenni.ai/ (20% off with code ANDY20)
• Wisio – https://www.wisio.app

AI academic editing tools

In the realm of scientific writing and editing, artificial intelligence (AI) tools are making a world of difference, offering precision and efficiency like never before. Consider tools such as Paper Pal, Writefull, and Trinka.

Together, these tools usher in a new era of scientific writing, where AI is your dedicated partner in the quest for impeccable composition.

• Paper Pal –  https://paperpal.com/
• Writefull –  https://www.writefull.com/
• Trinka –  https://www.trinka.ai/

AI tools for grant writing

In the challenging realm of science grant writing, two innovative AI tools are making waves: Granted AI and Grantable.

These platforms are game-changers, leveraging the power of artificial intelligence to streamline and enhance the grant application process.

Granted AI, an intelligent tool, uses AI algorithms to simplify the process of finding, applying, and managing grants. Meanwhile, Grantable offers a platform that automates and organizes grant application processes, making it easier than ever to secure funding.

Together, these tools are transforming the way we approach grant writing, using the power of AI to turn a complex, often arduous task into a more manageable, efficient, and successful endeavor.

• Granted AI – https://grantedai.com/
• Grantable – https://grantable.co/

Free AI research tools

There are many different tools online that are emerging for researchers to be able to streamline their research processes. There’s no need for convience to come at a massive cost and break the bank.

The best free ones at time of writing are:

• Elicit – https://elicit.org
• Connected Papers – https://www.connectedpapers.com/
• Litmaps – https://www.litmaps.com ( 10% off Pro subscription using the code “STAPLETON” )
• Consensus – https://consensus.app/

Wrapping up

The integration of artificial intelligence in the world of academic research is nothing short of revolutionary.

With the array of AI tools we’ve explored today – from research and mapping, literature review, peer-reviewed papers reading, scientific writing, to academic editing and grant writing – the landscape of research is significantly transformed.

The advantages that AI-powered research tools bring to the table – efficiency, precision, time saving, and a more streamlined process – cannot be overstated.

These AI research tools aren’t just about convenience; they are transforming the way we conduct and comprehend research.

They liberate researchers from the clutches of tedium and overwhelm, allowing for more space for deep exploration, innovative thinking, and in-depth comprehension.

Whether you’re an experienced academic researcher or a student just starting out, these tools provide indispensable aid in your research journey.

And with a suite of free AI tools also available, there is no reason to not explore and embrace this AI revolution in academic research.

We are on the precipice of a new era of academic research, one where AI and human ingenuity work in tandem for richer, more profound scientific exploration. The future of research is here, and it is smart, efficient, and AI-powered.

Before we get too excited however, let us remember that AI tools are meant to be our assistants, not our masters. As we engage with these advanced technologies, let’s not lose sight of the human intellect, intuition, and imagination that form the heart of all meaningful research. Happy researching!

Thank you to Ivan Aguilar – Ph.D. Student at SFU (Simon Fraser University), for starting this list for me!

Dr Andrew Stapleton has a Masters and PhD in Chemistry from the UK and Australia. He has many years of research experience and has worked as a Postdoctoral Fellow and Associate at a number of Universities. Although having secured funding for his own research, he left academia to help others with his YouTube channel all about the inner workings of academia and how to make it work for you.

Thank you for visiting Academia Insider.

We are here to help you navigate Academia as painlessly as possible. We are supported by our readers and by visiting you are helping us earn a small amount through ads and affiliate revenue - Thank you!

2024 © Academia Insider

Revolutionize Your Research with Jenni AI

Literature Review Generator

Welcome to Jenni AI, the ultimate tool for researchers and students. Our AI Literature Review Generator is designed to assist you in creating comprehensive, high-quality literature reviews, enhancing your academic and research endeavors. Say goodbye to writer's block and hello to seamless, efficient literature review creation.

Loved by over 1 million academics

Endorsed by Academics from Leading Institutions

Join the Community of Scholars Who Trust Jenni AI

Elevate Your Research Toolkit

Discover the Game-Changing Features of Jenni AI for Literature Reviews

Advanced AI Algorithms

Jenni AI utilizes cutting-edge AI technology to analyze and suggest relevant literature, helping you stay on top of current research trends.

Get started

Idea Generation

Overcome writer's block with AI-generated prompts and ideas that align with your research topic, helping to expand and deepen your review.

Built-In Plagiarism Checker

Ensure the originality of your work with an integrated plagiarism checker, minimizing the risk of accidental plagiarism.

Citation Assistance

Get help with proper citation formats to maintain academic integrity and attribute sources correctly.

Our Pledge to Academic Integrity

At Jenni AI, we are deeply committed to the principles of academic integrity. We understand the importance of honesty, transparency, and ethical conduct in the academic community. Our tool is designed not just to assist in your research, but to do so in a way that respects and upholds these fundamental values.

How it Works

Start by creating your account on Jenni AI. The sign-up process is quick and user-friendly.

Define Your Research Scope

Enter the topic of your literature review to guide Jenni AI’s focus.

Interact with AI-Powered Suggestions

Use Jenni AI’s suggestions to structure your literature review, organizing it into coherent sections.

Plagiarism Verification

Employ the integrated plagiarism checker to ensure the uniqueness of your work.

Citation Guidance

Receive assistance in citing sources correctly, maintaining the academic standard.

Easy Export

Export your literature review to LaTeX, HTML, or .docx formats

What Our Users Say

Discover how Jenni AI has made a difference in the lives of academics just like you

I thought AI writing was useless. Then I found Jenni AI, the AI-powered assistant for academic writing. It turned out to be much more advanced than I ever could have imagined. Jenni AI = ChatGPT x 10.

Charlie Cuddy

@sonofgorkhali

Love this use of AI to assist with, not replace, writing! Keep crushing it @Davidjpark96 💪

Waqar Younas, PhD

@waqaryofficial

4/9 Jenni AI's Outline Builder is a game-changer for organizing your thoughts and structuring your content. Create detailed outlines effortlessly, ensuring your writing is clear and coherent. #OutlineBuilder #WritingTools #JenniAI

I started with Jenni-who & Jenni-what. But now I can't write without Jenni. I love Jenni AI and am amazed to see how far Jenni has come. Kudos to http://Jenni.AI team.

Jenni is perfect for writing research docs, SOPs, study projects presentations 👌🏽

Stéphane Prud'homme

http://jenni.ai is awesome and super useful! thanks to @Davidjpark96 and @whoisjenniai fyi @Phd_jeu @DoctoralStories @WriteThatPhD

Frequently asked questions

What exactly does jenni ai do, is jenni ai suitable for all academic disciplines, how does jenni ai ensure the originality of my work, is there a trial period or a free version available.

How does Jenni AI help with writer's block?

Can Jenni AI write my literature review for me?

How often is the literature database updated in Jenni AI?

How user-friendly is Jenni AI for those not familiar with AI tools?

Jenni AI: Standing Out From the Competition

In a sea of online proofreaders, Jenni AI stands out. Here’s how we compare to other tools on the market:

Feature Featire

COMPETITORS

Advanced AI-Powered Assistance

Uses state-of-the-art AI technology to provide relevant literature suggestions and structural guidance.

May rely on simpler algorithms, resulting in less dynamic or comprehensive support.

Commitment to Academic Integrity

Strong focus on maintaining academic standards with built-in plagiarism checks and citation assistance.

Not all provide integrated plagiarism tools or may have less emphasis on citation guidelines.

User-Friendly Interface

Designed for ease of use, making it accessible for users with varying levels of tech proficiency.

Interfaces can be complex or less intuitive, posing a challenge for some users.

Transparent and Flexible Pricing

Offers a free trial and clear, flexible pricing plans suitable for different needs.

Pricing structures can be opaque or inflexible, with fewer user options.

Unparalleled Customization

Offers highly personalized suggestions and adapts to your specific research needs over time.

Often provide generic suggestions that may not align closely with individual research topics.

Comprehensive Literature Access

Provides access to a vast and up-to-date range of academic literature, ensuring comprehensive research coverage.

Some may have limited access to current or diverse research materials, restricting the scope of literature reviews.

Ready to Transform Your Research Process?

Don't wait to elevate your research. Sign up for Jenni AI today and discover a smarter, more efficient way to handle your academic literature reviews.

• Help Center

GET STARTED

COLLABORATE ON YOUR REVIEWS WITH ANYONE, ANYWHERE, ANYTIME

Save precious time and maximize your productivity with a Rayyan membership. Receive training, priority support, and access features to complete your systematic reviews efficiently.

Rayyan Teams+ makes your job easier. It includes VIP Support, AI-powered in-app help, and powerful tools to create, share and organize systematic reviews, review teams, searches, and full-texts.

RESEARCHERS

Rayyan makes collaborative systematic reviews faster, easier, and more convenient. Training, VIP support, and access to new features maximize your productivity. Get started now!

Over 500 million reference articles reviewed by research teams, and counting...

Intelligent, scalable and intuitive.

Rayyan understands language, learns from your decisions and helps you work quickly through even your largest systematic literature reviews.

WATCH A TUTORIAL NOW

Solutions for Organizations and Businesses

Rayyan Enterprise and Rayyan Teams+ make it faster, easier and more convenient for you to manage your research process across your organization.

• Accelerate your research across your team or organization and save valuable researcher time.
• Build and preserve institutional assets, including literature searches, systematic reviews, and full-text articles.
• Onboard team members quickly with access to group trainings for beginners and experts.
• Receive priority support to stay productive when questions arise.
• SCHEDULE A DEMO
• LEARN MORE ABOUT RAYYAN TEAMS+

RAYYAN SYSTEMATIC LITERATURE REVIEW OVERVIEW

LEARN ABOUT RAYYAN’S PICO HIGHLIGHTS AND FILTERS

Join now to learn why Rayyan is trusted by already more than 250,000 researchers

Individual plans, teams plans.

For early career researchers just getting started with research.

Free forever

• 3 Active Reviews
• Invite Unlimited Reviewers
• Import Directly from Mendeley
• Industry Leading De-Duplication
• 5-Star Relevance Ranking
• Advanced Filtration Facets
• Mobile App Access
• 100 Decisions on Mobile App
• Standard Support
• Revoke Reviewer
• Online Training
• PICO Highlights & Filters
• PRISMA (Beta)
• Auto-Resolver 
• Multiple Teams & Management Roles
• Monitor & Manage Users, Searches, Reviews, Full Texts
• Onboarding and Regular Training

Professional

For researchers who want more tools for research acceleration.

Per month billed annually

• Unlimited Active Reviews
• Unlimited Decisions on Mobile App
• Priority Support
• Auto-Resolver

For students who want more tools to accelerate their research.

Per month billed annually

Billed monthly

For a team that wants professional licenses for all members.

Per-user, per month, billed annually

• Single Team
• High Priority Support

For teams that want support and advanced tools for members.

• Multiple Teams
• Management Roles

For organizations who want access to all of their members.

Annual Subscription

Contact Sales

• Organizational Ownership
• For an organization or a company
• Access to all the premium features such as PICO Filters, Auto-Resolver, PRISMA and Mobile App
• Store and Reuse Searches and Full Texts
• A management console to view, organize and manage users, teams, review projects, searches and full texts
• Highest tier of support – Support via email, chat and AI-powered in-app help
• GDPR Compliant
• Single Sign-On
• API Integration
• Training for Experts
• Training Sessions Students Each Semester
• More options for secure access control

ANNUAL ONLY

Per-user, billed monthly

Rayyan Subscription

membership starts with 2 users. You can select the number of additional members that you’d like to add to your membership.

Total amount:

Click Proceed to get started.

Great usability and functionality. Rayyan has saved me countless hours. I even received timely feedback from staff when I did not understand the capabilities of the system, and was pleasantly surprised with the time they dedicated to my problem. Thanks again!

This is a great piece of software. It has made the independent viewing process so much quicker. The whole thing is very intuitive.

Rayyan makes ordering articles and extracting data very easy. A great tool for undertaking literature and systematic reviews!

Excellent interface to do title and abstract screening. Also helps to keep a track on the the reasons for exclusion from the review. That too in a blinded manner.

Rayyan is a fantastic tool to save time and improve systematic reviews!!! It has changed my life as a researcher!!! thanks

Easy to use, friendly, has everything you need for cooperative work on the systematic review.

Rayyan makes life easy in every way when conducting a systematic review and it is easy to use.

AI Assistance in Academia for Searching Credible Scholarly Sources

The journey of academia is a grand quest for knowledge, more specifically an adventure to find the right information through credible sources, and that’s where scholarly sources walk in. As the name suggests, it simply means that such sources are written by scholars and experts of a specialized field. These sources are in the form of journal articles, books, conference publications, or websites. Such resources undergo a stringent peer-review process by a panel of subject matter experts. Thus, the findings presented are credible and refined. In contrast, popular sources, such as newspapers, magazines, and blogs, often lack the meticulous scrutiny of peer review and may prioritize approachability over technical accuracy.

Let’s explore the key points of difference between scholarly sources and popular sources:

Table of Contents

Why Cite Scholarly Sources When Writing Your Research Paper?

Selecting scholarly sources is a strategic decision that affects your research outcome, as it builds the foundation of your academic work. It plays a crucial role for individuals at every stage of their academic journey, benefiting both early-career and established researchers. It allows scholars to actively participate in academic conversations by sharing valuable insights in their field, inspiring others in the research area to make advancements. Furthermore, for a university student, making their first stride in scholarly research, it enhances their knowledge and serves as a gateway to join the scholarly community.

Curious about the nuances of literature review in academia? Take our short quiz now to deepen your understanding of this essential academic practice.

Fill the Details to Check Your Score

Exploring Barriers in Scholarly Literature Search

Exploring today’s vast information landscape is like finding a needle in a haystack. This mirrors the challenges researchers face with the overwhelming number of scholarly articles in today’s digital age. According to the National Center for Science and Engineering Statistics , scientists publish nearly 3 million publications each year. A simple query search on platforms like Google Scholar can result in an overwhelming number of articles, posing a challenge to navigate through them and gain a comprehensive overview. Furthermore, such scholarly search platforms often fail to reveal new findings in a particular field as the system tends to favor highly cited , older articles.

Modern researchers and students face further complex challenges as science becomes more specialized, introducing peculiar jargon and keywords. This coupled with the multidisciplinary nature of research, can result in overlooking valuable findings from other fields due to specific jargon and knowledgebase constraints. Other challenges include identifying and selecting relevant resources due to the diverse formats in which information is presented (journal articles, preprints, conference posters, etc.), selecting which literature to choose with precision to prevent unintended plagiarism , and software limitations in managing literature sources in different formats.

Understanding the Use of AI Research Assistance Tools for Reliable Scholarly Sources

In this world of the internet, where a single click generates thousands of search results, AI research assistance tools can guide you through this chaos to the right scholarly source. These tools automate the process of identifying reliable papers, finding and summarizing relevant sections of a research paper , analyzing it to bridge knowledge gaps, and generating potential project ideas. Listed below are the pros and cons of such tools to help you make informed decisions when incorporating these tools into your research workflow:

4 Essential Research Assistance AI Tools

Currently, there are numerous AI-based tools with a wide range of capabilities for literature review assistance , each tailored to specific requirements. It is imperative to make an informed decision based on certain evaluation parameters that sets each of these tools apart. Simplifying this choice for you, we have compared 4 most useful AI research assistance tools to understand their distinctiveness:

Here is a comprehensive analysis of 4 most useful AI research assistance tools for a thorough understanding of their capabilities:

1. Semantic Scholar

Semantic scholar is an AI-powered search engine that:

• Conducts contextual analysis of papers.
• Offers advanced citation analysis and automates the process of identifying relevant research papers from its database of over 200 million papers for literature reviews.
• Bridges knowledge gaps and prompts project ideas.

2. Enago Read

Enago Read offers several features to enhance the experience of researchers for literature exploration and research process. They include:

• Summarizes key sections of papers, allowing for quick insight into the content of a research article.
• Supports inline attachments, ensuring a seamless organization of project-related files.
• Provides AI-powered suggestions to discover related research material and stay updated with relevant news from the large data repository of 170+ million research papers.
• Promotes enhanced collaboration and structured note-taking for better team communication, accelerating the process of literature review and critical reading.
• Streamlines the management of references , contributing to a more efficient and organized research workflow.

Scite is an AI research tool that:

• Provides services to enhance the research experience, including smart citations that support, contrast, and mention relevant content
• Presents citation contexts with accompanying text excerpts, allowing for a more in-depth understanding from over 181 million papers.
• Facilitates thorough literature reviews, making it a valuable tool for researchers engaging in systematic reviews and meta-analyses

4. Connected Papers

Connected Papers aids in identifying gaps in literature reviews in the following ways:

• Provides valuable insights for your scholarly venture
• Visualizes the research landscape, helping you identify key papers and trends
• Deepens your understanding of research relationships by exploring paper interconnections

While many AI research assistant tools help in identifying and storing scholarly sources, the real challenge is in efficiently connecting them. You must try and choose a platform that acts as an all-in-one solution. A platform that promotes your research needs, enabling you to execute literature analysis, collaborate with your team, identify research gaps, draft, and explore the journey of research.

Have you used any of the mentioned AI research assistance tools to find reliable scholarly sources and analyze them? Let us know how this article has contributed to your journey in finding the right research source for you. Also, don’t forget to share your preferred AI tool for academic research on Enago Academy’s Open Platform .

Frequently Asked Questions

Scholarly sources are academic sources written by subject-matter experts, and are subject to the process of peer review. This process ensures that the information in such sources is updated, scientifically accurate, and of excellent quality.

The examples of scholarly sources include journal articles, books, conference publications, dissertations, and even websites.

Citing sources is ethically important as it enhances the credibility of your work and prevents plagiarism. It also ensures that the credit is given where it is due.

Scholarly sources are important for academic research as they present accurate and updated information that is free of bias and is objective in nature.

Rate this article Cancel Reply

Your email address will not be published.

Enago Academy's Most Popular Articles

• AI in Academia
• Trending Now

6 Leading AI Detection Tools for Academic Writing — A comparative analysis

The advent of AI content generators, exemplified by advanced models like ChatGPT, Claude AI, and…

• Industry News

Controversy Erupts Over AI-Generated Visuals in Scientific Publications

In recent months, the scientific community has been grappling with a growing trend: the integration…

• Reporting Research

How to Improve Lab Report Writing: Best practices to follow with and without AI-assistance

Imagine you’re a scientist who just made a ground-breaking discovery! You want to share your…

EU AI Act: Charting a new course for AI governance and research

In a landmark move, the European Union (EU) is set to introduce the world’s first…

ICMJE Updates Guidelines for Medical Journal Publication, Emphasizes on Inclusivity and AI Transparency

The International Committee of Medical Journal Editors (ICMJE) recently updated its recommendations for best practices…

How to Improve Lab Report Writing: Best practices to follow with and without…

AI for Accuracy in Research and Academic Writing

Upholding Academic Integrity in the Age of AI: Challenges and solutions

Preserving Research Integrity: Why author guidelines on generative AI tools matter

Sign-up to read more

Subscribe for free to get unrestricted access to all our resources on research writing and academic publishing including:

• 2000+ blog articles
• 50+ Webinars
• 10+ Expert podcasts
• 50+ Infographics
• 10+ Checklists
• Research Guides

We hate spam too. We promise to protect your privacy and never spam you.

I am looking for Editing/ Proofreading services for my manuscript Tentative date of next journal submission:

What should universities' stance be on AI tools in research and academic writing?

We generate robust evidence fast

What is silvi.ai    .

Silvi is an end-to-end screening and data extraction tool supporting Systematic Literature Review and Meta-analysis.

Silvi helps create systematic literature reviews and meta-analyses that follow Cochrane guidelines in a highly reduced time frame, giving a fast and easy overview. It supports the user through the full process, from literature search to data analyses. Silvi is directly connected with databases such as PubMed and ClinicalTrials.gov and is always updated with the latest published research. It also supports RIS files, making it possible to upload a search string from your favorite search engine (i.e., Ovid). Silvi has a tagging system that can be tailored to any project.

Silvi is transparent, meaning it documents and stores the choices (and the reasons behind them) the user makes. Whether publishing the results from the project in a journal, sending them to an authority, or collaborating on the project with several colleagues, transparency is optimal to create robust evidence.

Silvi is developed with the user experience in mind. The design is intuitive and easily available to new users. There is no need to become a super-user. However, if any questions should arise anyway, we have a series of super short, instructional videos to get back on track.

To see Silvi in use, watch our short introduction video.

  Short introduction video  

Learn more about Silvi’s specifications here.

"I like that I can highlight key inclusions and exclusions which makes the screening process really quick - I went through 2000+ titles and abstracts in just a few hours"

Eishaan Kamta Bhargava 

Consultant Paediatric ENT Surgeon, Sheffield Children's Hospital

"I really like how intuitive it is working with Silvi. I instantly felt like a superuser."

Henriette Kristensen

Senior Director, Ferring Pharmaceuticals

"The idea behind Silvi is great. Normally, I really dislike doing literature reviews, as they take up huge amounts of time. Silvi has made it so much easier! Thanks."

Claus Rehfeld

Senior Consultant, Nordic Healthcare Group

"AI has emerged as an indispensable tool for compiling evidence and conducting meta-analyses. Silvi.ai has proven to be the most comprehensive option I have explored, seamlessly integrating automated processes with the indispensable attributes of clarity and reproducibility essential for rigorous research practices."

Martin Södermark

M.Sc. Specialist in clinical adult psychology

Silvi.ai was founded in 2018 by Professor in Health Economic Evidence, Tove Holm-Larsen, and expert in Machine Learning, Rasmus Hvingelby. The idea for Silvi stemmed from their own research, and the need to conduct systematic literature reviews and meta-analyses faster.

The ideas behind Silvi were originally a component of a larger project. In 2016, Tove founded the group “Evidensbaseret Medicin 2.0” in collaboration with researchers from Ghent University, Technical University of Denmark, University of Copenhagen, and other experts. EBM 2.0  wanted to optimize evidence-based medicine to its highest potential using Big Data and Artificial Intelligence, but needed a highly skilled person within AI.

Around this time, Tove met Rasmus, who shared the same visions. Tove teamed up with Rasmus, and Silvi.ai was created.

Our story  

       Free Trial       

    No   card de t ails nee ded!  

• Research Guides
• University Libraries

AI-Based Literature Review Tools

• Dialogues: Insightful Facts
• How to Craft Prompts
• Plugins / Extensions for AI-powered Searches
• Cite ChatGPT in APA / MLA
• AI and Plagiarism
• ChatGPT & Higher Education
• Author Profile

Selected AI-Based Literature Review Tools

Updates: See news or release of AI (Beta) across various academic research databases including Web of Science , Scopus , Ebsco , ProQues t, OVID , Dimensions , JStor , Westlaw , and LexisNexis . ********* ********** ********** ********** **********   

Disclaimer: TAMU libraries do not have subscription access to the AI-powered tools listed below the divider line. The guide serves solely as an informational resource. It is recommended that you assess these tools and their usage methodologies independently. ------------------------------------------------------------------------------------------------------------------------------------------------------------- SEMANTIC SCHOLAR

• SCIENTIFIC LITERATURE SEARCH ENGINE - finding semantically similar research papers.
• " A free, AI-powered research tool for scientific literature."  <https://www.semanticscholar.org/>. But login is required in order to use all functions.
• Over 200 millions of papers from all fields of science, the data of which has also served as a wellspring for the development of other AI-driven tools.

The 4000+ results can be sorted by Fields of Study, Date Range, Author, Journals & Conferences

Save the papers in your Library folder. The Research Feeds will recommend similar papers based on the items saved.

Example - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality Total Citations: 22,438   [Note: these numbers were gathered when this guide was created] Highly Influential Citations 2,001 Background Citations 6,109 Methods Citations 3,273  Results Citations 385

TLDRs (Too Long; Didn't Read) Try this example . Press the pen icon to reveal the highlighted key points . TLDRs "are super-short summaries of the main objective and results of a scientific paper generated using expert background knowledge and the latest GPT-3 style NLP techniques. This new feature is available in beta for nearly 60 million papers in computer science, biology, and medicine..." < https://www.semanticscholar.org/product/tldr>

• AI-POWERED RESEARCH ASSISTANT - finding papers, filtering study types, automating research flow, brainstorming, summarizing and more.
• " Elicit is a research assistant using language models like GPT-3 to automate parts of researchers’ workflows. Currently, the main workflow in Elicit is Literature Review. If you ask a question, Elicit will show relevant papers and summaries of key information about those papers in an easy-to-use table."   <https://elicit.org/faq#what-is-elicit.>; Find answers from 175 million papers. FAQS
• Example - How do mental health interventions vary by age group?    /   Fish oil and depression Results: [Login required] (1) Summary of top 4 papers > Paper #1 - #4 with Title, abstract, citations, DOI, and pdf (2) Table view: Abstract / Interventions / Outcomes measured / Number of participants (3) Relevant studies and citations. (4) Click on Search for Paper Information to find - Metadata about Sources ( SJR etc.) >Population ( age etc.) >Intervention ( duration etc.) > Results ( outcome, limitations etc.) and > Methodology (detailed study design etc.) (5) Export as BIB or CSV
• How to Search / Extract Data / List of Concept Search -Enter a research question >Workflow: Searching > Summarizing 8 papers> A summary of 4 top papers > Final answers. Each result will show its citation counts, DOI, and a full-text link to Semantic Scholar website for more information such as background citations, methods citation, related papers and more. - List of Concepts search - e.g. adult learning motivation . The results will present a list the related concepts. - Extract data from a pdf file - Upload a paper and let Elicit extract data for you.
• Export Results - Various ways to export results.
• How to Cite - Includes the elicit.org URL in the citation, for example: Ought; Elicit: The AI Research Assistant; https://elicit.org; accessed xxxx/xx/xx

CONSENSUS.APP

ACADEMIC SEARCH ENGINE- using AI to find insights in research papers.

"We are a search engine that is designed to accept research questions, find relevant answers within research papers, and synthesize the results using the same language model technology." <https://consensus.app/home/blog/maximize-your-consensus-experience-with-these-best-practices/>

• Example - Does the death penalty reduce the crime?   /  Fish oil and depression  /    (1) Extracted & aggregated findings from relevant papers. (2) Results may include AIMS, DESIGN, PARTICIPANTS, FINDINGS or other methodological or report components. (3) Summaries and Full Text
• How to Search Direct questions - Does the death penalty reduce the crime? Relationship between two concepts - Fish oil and depression / Does X cause Y? Open-ended concepts - effects of immigration on local economics Tips and search examples from Consensus' Best Practice   
• Synthesize (beta) / Consensus Meter When the AI recognizes certain types of research questions, this functionality may be activated. It will examine a selection of some studies and provide a summary along with a Consensus Meter illustrating their collective agreement. Try this search: Is white rice linked to diabetes? The Consensus Meter reveals the following outcomes after analyzing 10 papers: 70% indicate a positive association, 20% suggest a possible connection, and 10% indicate no link.

Prompt “ write me a paragraph about the impact of climate change on GDP with citations “

CITATIONS IN CONTEXT

Integrated with Research Solutions.

Over 1.2 billion Citation Statements and metadata from over 181 million papers suggested reference.

How does it work? - "scite uses access to full-text articles and its deep learning model to tell you, for a given publication: - how many times it was cited by others - how it was cited by others by displaying the text where the citation happened from each citing paper - whether each citation offers supporting or contrasting evidence of the cited claims in the publication of interest, or simply mention it."   <https://help.scite.ai/en-us/article/what-is-scite-1widqmr/>

EXAMPLE of seeing all citations and citation statements in one place

More information: Scite: A smart citation index that displays the context of citations and classifies their intent using deep learning  

• GPT3.5 by OpenAI. Knowledge cutoff date is September 2021.
• Input/ Output length - ChatGPT-3.5 allows a maximum token limit of 4096 tokens. According to ChatGPT " On average, a token in English is roughly equivalent to 4 bytes or characters. English words are typically around 5 characters long. This means that, very roughly, you could fit around 800 to 1000 English words within 4096 tokens." 
• According to ChatGPT, the generated responses are non-deterministic by default. So if you run the searches again and get slightly or very different results, it's likely due to this factor.
• ChatGPT may find non-existent references.
• According to this study < https://arxiv.org/ftp/arxiv/papers/2304/2304.06794.pdf > "ChatGPT cites the most-cited articles and journals, relying solely on Google Scholar's citation counts" within the field of environmental science.  
• Example - "INTERVIEW WITH CHATGPT" as a Research Method & Teaching Tool Some researchers began to use this approach to obtain their research data. Try this Google Scholar search link "interview with ChatGPT"   or see two articles below: (1) Chatting about ChatGPT: how may AI and GPT impact academia and libraries? BD Lund, T Wang - Library Hi Tech News, 2023 (2) An interview with ChatGPT: discussing artificial intelligence in teaching, research, and practice , G Scaringi, M Loche - 2023  

Increased risk of sudden infant death syndrome (SIDS) Increased risk of premature birth Increased risk of low birth weight Increased risk of respiratory problems in newborns Increased risk of respiratory problems in infants exposed to secondhand smoke Increased risk of developing asthma and other respiratory illnesses later in life for infants exposed to secondhand smoke [Note : ChatGPT may generate non-existent references or false knowledge. To find out why Large Language Models hallucinate, check out this Wiki article: Hallucination (artificial intelligence) and this blog post -   A Gentle Introduction to Hallucinations in Large Language Models by Adrian Tam ]

Infant death Neonatal mortality (referring specifically to deaths within the first 28 days of life) Perinatal mortality (referring to deaths occurring during the period from 22 completed weeks of gestation to 7 completed days after birth) Early childhood mortality (referring to deaths occurring within the first five years of life) Child mortality (referring to deaths occurring before the age of 18) [Press the Regenerate button to get more.]

• Example -  RELATED WORDS What are the related words of infant mortality? Neonatal mortality, Post-neonatal mortality, Stillbirths, Low birth weight, Malnutrition, Infectious diseases, Vaccination, Maternal health,  Access to healthcare, Poverty, Social inequality, Sanitation, Hygiene, Water quality, Childbirth complications, Congenital abnormalities, Birth defects, Maternal age, Under-five mortality, Child mortality, Perinatal mortality, Preterm birth, Low birth weight, Sudden infant death syndrome (SIDS), Maternal mortality, Postnatal care, Malnutrition, Immunization, Access to healthcare, Clean water and sanitation, Congenital anomalies, Infant health disparities, Infant mortality rate (IMR), Infant survival.  

(("Infant Death"[Mesh] OR "Sudden Infant Death Syndrome"[Mesh] OR "Infant Mortality"[Mesh] OR "Perinatal Mortality"[Mesh] OR "Neonatal Mortality"[Mesh] OR "Fetal Mortality"[Mesh] OR "Infant Death" OR "Sudden Infant Death Syndrome" OR "Infant Mortality" OR "Perinatal Mortality" OR "Neonatal Mortality" OR "Fetal Mortality") AND ("Risk Factors"[Mesh] OR "Etiology"[Mesh] OR "Prevention and Control"[Mesh] OR "Interventions"[Mesh] OR "Public Health"[Mesh] OR "Health Disparities"[Mesh] OR "Healthcare Disparities"[Mesh] OR "Poverty"[Mesh] OR "Malnutrition"[Mesh] OR "Infection"[Mesh] OR "Congenital Abnormalities"[Mesh] OR "Prematurity"[Mesh] OR "Low Birth Weight"[Mesh] OR "Maternal Education"[Mesh] OR "Maternal Health"[Mesh] OR "Risk Factors" OR "Etiology" OR "Prevention and Control" OR "Interventions" OR "Public Health" OR "Health Disparities" OR "Healthcare Disparities" OR "Poverty" OR "Malnutrition" OR "Infection" OR "Congenital Abnormalities" OR "Prematurity" OR "Low Birth Weight" OR "Maternal Education" OR "Maternal Health")) Comments and Suggestions: #1 -This search string may not work on all database platforms. For example, Medline (OVID) may not be able to run it, Medline & CINAHL (EBSCO) can run it without any problems while PubMed will run it but it will indicate which MeSH terms are not indexed. See PubMed's search History and Details under Advanced . #2 - This is just one possible combination. You may need to adjust it based on your task and the databases you are using . #3 - It might be easier if you break the task into 3 parts: ask for synonyms > ask for thesauri terms > and ask it to combine them.

Examples - DATABASE RECOMMENDATIONS Heath Science - Which databases to use to find articles on the EFFECTS OF MATERNAL SMOKING ON INFANT DEATH? PubMed: This is a database of biomedical literature from the National Library of Medicine. It includes articles from medical journals and other sources on a wide range of health-related topics. Embase: This is a database of biomedical literature that covers more international and pharmaceutical content than PubMed. It includes articles from medical journals and other sources on a wide range of health-related topics. Cochrane Library : This is a collection of databases that provides systematic reviews and meta-analyses of healthcare interventions, including interventions related to maternal smoking and infant death. Scopus: This is a multidisciplinary database that covers research from a wide range of fields, including health sciences. It includes articles from scientific journals, books, and conference proceedings. Web of Science: This is a database that covers research from a wide range of fields, including health sciences. It includes articles from scientific journals, books, and conference proceedings. CINAHL: This is a database of nursing and allied health literature, including articles on maternal smoking and infant death. [Note: The response above was copied and pasted directly from ChatGPT. No editing was added.] Education -- I am doing a meta-analysis on k-12 STEM education. What databases should I use? ERIC : This is a database of education research and information, including articles from journals, reports, and conference papers. It is a commonly used database for educational research. Education Source : This is a comprehensive database of education research and information, including articles from journals, books, and conference papers. Web of Science: This is a multidisciplinary database that covers research from a wide range of fields, including education. It includes articles from scientific journals, books, and conference proceedings. Scopus: This is another multidisciplinary database that covers research from a wide range of fields, including education. It includes articles from scientific journals, books, and conference proceedings. PsycINFO: This is a database of psychology research, including articles from journals, books, and dissertations. It can be useful for research on STEM education that includes psychological factors. Cochrane Library : This is a collection of databases that provides systematic reviews and meta-analyses of healthcare interventions including interventions related to education. [Author's note: You could also ask for the GREY LITERATURE sources related to the topic above,]

Example: ACT-AS-AN-EXPERT PROMPT Here's an alternative way to consolidate all the questions into a single consultation by using this popular Act-As-An-Expert prompt, aka, system message prompt:  I am going to conduct a systematic review on games and mathematics related to K-12 education  I want you to act as a systematic review expert . I will ask you some questions related to my research topic and you advise me on how to do it. 

[You may ask one question at a time] My first question is "which databases should I use?"  My second question is "what are the relevant subject terms, descriptors and key words?" My third question is "how to do data extraction?" ..... , .... Please note that the above prompts are merely for illustrative purposes. Actual questions may contain more specific instructions. As an example, for the first question, could you provide guidance on how to identify relevant publications? Specifically, can you provide a list of the primary databases and grey literature sources related to my topic?  

Example - GREY LITERATURE Please show me all the resources that offer grey literature for conducting research in the field of education     ERIC (Education Resources Information Center): https://eric.ed.gov/     OpenGrey: http://www.opengrey.eu/     British Education Index: https://www.ebscohost.com/academic/british-education-index     WorldCat: https://www.worldcat.org/     ProQuest Dissertations & Theses Global: https://www.proquest.com/products-services/pqdtglobal.html     EThOS (Electronic Theses Online Service): https://ethos.bl.uk/     Institutional Repositories of universities and academic institutions (search for specific institution repositories)     American Educational Research Association (AERA): https://www.aera.net/     National Education Association (NEA): https://www.nea.org/     Association for Supervision and Curriculum Development (ASCD): http://www.ascd.org/     RAND Corporation: https://www.rand.org/     National Center for Education Research (NCER): https://ies.ed.gov/ncer/     National Center for Education Statistics (NCES): https://nces.ed.gov/     European Educational Research Association (EERA): https://www.eera-ecer.de/     UNESCO International Institute for Educational Planning (IIEP): http://www.iiep.unesco.org/     Organization for Economic Cooperation and Development (OECD): https://www.oecd.org/education/     Education Development Center (EDC): https://www.edc.org/     National Institute for Educational Policy Research (NIER) - Japan: https://www.nier.go.jp/     Australian Council for Educational Research (ACER): https://www.acer.org/     Canadian Education Association (CEA): https://www.cea-ace.ca/ My topic is about stem education. Which grey literature databases should I use?    STEM Education Research Centre (SERC) Grey Literature Database    National STEM Education Research Repository (NSERR)    National Science Digital Library (NSDL)    STEM Education Resource Center (SERC) GrayLit Network    STEM Education Grey Literature Library

See other Comparison Examples under Bing AI.

Examples - ZERO SHOT, ONE SHOT & FEW SHOT PROMPTING for literature review See the examples on the left panel- How to Fine Tune Prompts

Bing Chat / Copilot

• Bing Chat has become Copilot.
• CONVERSATIONAL LLM 4.0 + SEARCH ENGINE. Connects to the Internet.
• Three conversation modes: More Creative, More Balanced or More Precise.
• Comparison - Prompt: My topic is about psychology. Which grey literature databases should I use? More Precise - PsycExtra, NIH Library and links to library guides, .gov and .org websites More Balanced - PsycExtra and three main research guides that mention psychology grey literature sources. More Creative- PsycExtra, LILACS, and Worldcat + definition of grey literature + suggestions on searching for professional association websites, newsletters, magazines, standards and guidelines, and other sources that may contain relevant information for your topic.
• Some examples below were tested in Bing Chat only.  
• Example - factors of infant mortality Infant mortality is a term that refers to the death of infants before their first birthday. The leading causes of infant mortality include birth asphyxia, pneumonia, congenital malformations, term birth complications such as abnormal presentation of the fetus umbilical cord prolapse, or prolonged labor, neonatal infection, diarrhea, malaria, measles, and malnutrition1. Many situational factors lead to infant mortality such as the pregnant woman’s level of education, environmental conditions, political infrastructure, and level of medical support1. In the United States, a primary determinant of infant mortality risk is infant birth weight with lower birth weights increasing the risk of infant mortality. The determinants of low birth weight include socioeconomic, psychological, behavioral and environmental factors2.  
• Example: PEER REVIEWED SOURCES I need to find some peer reviewed articles about infant mortality? The answer includes 5 articles. The first one is “Causes of death and infant mortality rates among full-term births in the United States between 2010 and 2012: An observational study” by Neha Bairoliya and Günther Fink1. A click on  " Tell me more about the first article " leads to this summary: " The first article is titled “Causes of death and infant mortality rates among full-term births in the United States between 2010 and 2012: An observational study” and was published in PLOS Medicine on March 20, 2018. The authors are Neha Bairoliya and Günther Fink. The study used linked birth and death records for the period 2010–2012 to identify the state- and cause-specific burden of infant mortality among full-term infants (born at 37–42 weeks of gestation) in the United States. The researchers found that the full-term infant mortality rate (FTIMR) was 2.2 per 1,000 live births overall and ranged between 1.29 (Connecticut) and 3.77 (Mississippi) at the state level. Sudden unexpected death in infancy (SUDI) accounted for 43% of FTIM; congenital malformations and perinatal conditions accounted for 31% and 11.3% of FTIM, respectively. The largest mortality differentials between states with good and states with poor FTIMR were found for SUDI, with particularly large risk differentials for deaths due to sudden infant death syndrome (SIDS) and suffocation." More searches: Please find five empirical studies focusing on the factors influencing adult learners engaged in online education. Please locate five scholarly articles on stress management among college students site:pubmed.ncbi.nlm.nih.gov

The ERIC Thesaurus contains nearly 12,000 terms, including more than 4,500 descriptors and 7,000 synonyms1. You can use the term “Academic Achievement” or its synonyms such as “Educational Achievement”, “Student Achievement”, “Academic Performance”, “Academic Success”, “Learning Achievement” and more. [ Note : The follow-up responses include some additional sources. See two below: https://www.powerthesaurus.org/academic_achievement https://eric.ed.gov/?ti=Achievement+Gap   including https://eric.ed.gov/?ti=Academic+Achievement |

My topic is about psychology.  Which grey literature databases should I use?

ChatGPT PsycEXTRA : This database is produced by the American Psychological Association (APA) and includes grey literature such as conference papers, white papers, and government reports. OpenGrey : This database provides access to grey literature produced in Europe, including reports, theses, and conference papers Grey Literature Report : This database is produced by The New York Academy of Medicine and includes reports, conference papers, and other grey literature on health and biomedical topics, including psychology. ProQuest Dissertations and Theses Global : This database provides access to graduate-level research, including theses and dissertations related to psychology. Google Scholar: While not exclusively a grey literature database, Google Scholar can be a useful tool for finding conference papers and other grey literature related to psychology. National Technical Information Service (NTIS) : This database provides access to technical reports produced by U.S. government agencies, including those related to psychology. Bing AI   - [asked in the Precise mode] For psychology, some recommended grey literature databases include PsycEXTRA and PsyArXiv . PsycEXTRA is a database of grey literature material relating to psychology, behavioral sciences and health. PsyArXiv is a psychology archive designed to facilitate rapid dissemination of psychological research. What other models have been developed based on SERVQUAL?

ChatGPT SERVPERF: This is a modified version of SERVQUAL that measures service performance instead of service quality. It was developed by Cronin and Taylor (1992) and is based on the same five dimensions as SERVQUAL. SERVPERF-GAP: This model, developed by Caruana and Ewing (2006), extends the SERVQUAL model to include three additional gaps that can occur when customers evaluate service quality. E-SERVQUAL: This model, developed by Parasuraman et al. (2005), adapts the SERVQUAL scale to measure the quality of online services. SERVCO: This is a modified version of SERVQUAL that includes a sixth dimension, "cost," in addition to the five original dimensions. It was developed by Sureshchandar et al. (2002) to address the importance of cost in service quality evaluation. SERVQ-HC: This is a modified version of SERVQUAL that is specifically designed for evaluating the quality of health care services. It was developed by Cronin et al. (2000) and includes 20 items across five dimensions. Bing AI The Nordic model of service quality2. The hierarchical model of service quality3. The American Customer Satisfaction Index (ACSI)4.

     Bing AI Sidebar - CHAT, THINK, & WRITE

• Examples of Using AI sidebar to Recap Google Scholar findings

Chat - If you highlight a study in the search results of Google Scholar, you will be prompted with a question by AI sidebar asking if you want to send the selected text to it. If you choose to do so, you can then select either  EXPLAIN or EXPAND to learn more about the chosen article. It's worth noting that EXPAND provides more detailed information. You can then click on any of the follow-up links to delve further into the selected article or topic. If the text of the chosen study is written in a foreign language, the AI sidebar can also provide an explanation of the text in English. Another option for extracting the key points from a selected article is to submit the URL of the PDF. Insights - Use the insights button to get more ideas about the topic. Compose - Tell the Edge sidebar your topic and let its Compose tool to generate a draft for you. Google Scholar Button- See also the Plugins and Extension page for how to perform a combined search using Google, Google Scholar, and ChatGPT .

Example: FINDING SIMILAR ARTICLES Find similar articles like this one - [then paste in the abstract ] Note - Use this prompt with Bing chat since real-time web info is required.

Examples: SUMMARIZE + REFERENCE Use a basic prompt like " Please summarize . ..." or add a REFERENCE TEXT that provides the necessary information about what you want it to focus or how the summary or resolution should look like. The reference could be a quote, an excerpt, a partial sentence, a conversation, an abstract, a code snippet and so on. Formula : Specify a role > assign a task > provide a reference text. Example#1 - Scholarly Journal Quote

STEP 1 Prompt: As a research assistant specializing in renewable energy, your task is to locate comparable research studies based on the provided abstract from an article: "This paper discusses the perspective of renewable energy (wind, solar, wave and biomass) in the making of strategies for a sustainable development. Such strategies typically involve three major technological changes: energy savings on the demand side, efficiency improvements in the energy production, and replacement of fossil fuels by various sources of renewable energy."

Bing Chat then found 3 documents: the ScienceDirect paper where the abstract came from and two other documents from un.org and frontiersin.org respectively.

STEP 2 Prompt: Please synthesize the findings of the three studies provided above.

Bing Chat: "Sure! Here is a synthesis of the findings from the three studies:

All three studies emphasize the importance of renewable energy in achieving sustainable development and mitigating climate change. They all discuss various strategies and actions that can be taken to increase the use of renewable energy sources and reduce reliance on fossil fuels.

Henrik Lund’s paper discusses the perspective of renewable energy (wind, solar, wave and biomass) in the making of strategies for a sustainable development. Such strategies typically involve three major technological changes: energy savings on the demand side, efficiency improvements in the energy production, and .....

The United Nations outlines five critical actions the world needs to prioritize now to transform our energy systems and speed up the shift to renewable energy: Make renewable energy technology a global public good, Improve global access to components and raw materials......

“Sustainable Energy Transition for Renewable and Low Carbon Grid” discusses that a sustainable global electricity transition will entail increased use of renewable energy sources particularly wind and solar, nuclear energy as a low carbon energy source, electrification of transport and.......

In summary , these studies suggest that transitioning to renewable energy sources is crucial for sustainable development and mitigating climate change. This can be achieved through various strategies such as increasing energy efficiency, improving access to renewable technology and materials, leveling the playing field for renewables, ending fossil fuel subsidies, and redirecting investments towards renewables." Example #2 Y ou are an expert researcher, given the following article, please discuss its key findings. Reference: How Large Language Models are Transforming Machine-Paraphrased Plagiarism at https://arxiv.org/abs/2210.03568 This is another way to put REFERENCE TEXT. As a side not, role specifying or the use of persona is important as it can impact the level of responses obtained. Just imagine if the designated role were " You are a high school student... ." Example #3 Please read this article and summarize it f or me - "Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making" and then find 5 similar studies and please also summarize each for me.

CONNECTED PAPERS

• RELATED STUDIES
• Uses visual graphs or other ways to show relevant studies. The database is connected to the Semantic Scholar Paper Corpus which has compiled hundreds of millions of published papers across many science and social science fields.
• See more details about how it works .  
• Example - SERVQUAL and then click on SELECT A PAPER TO BUILD THE GRAPH > The first paper was selected. Results: (1) Origin paper - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality + Connected papers with links to Connected Papers / PDF / DOI or Publisher's site / Semantic Scholar / Google Scholar. (2) Graph showing the origin paper + connected papers with links to the major sources . See above. (3) Links to Prior Works and Derivative Works See the detailed citations by Semantic Scholar on the origin SERVQUAL paper on the top of this page within Semantic Scholars.
• How to Search Search by work title. Enter some keywords about a topic.
• Download / Save Download your saved Items in Bib format.

PAPER DIGEST

• SUMMARY & SYNTHESIS
• " Knowledge graph & natural language processing platform tailored for technology domain . <"https://www.paperdigest.org/> Areas covered: technology, biology/health, all sciences areas, business, humanities/ social sciences, patents and grants ...

• LITERATURE REVIEW - https://www.paperdigest.org/review/ Systematic Review - https://www.paperdigest.org/literature-review/
• SEARCH CONSOLE - https://www.paperdigest.org/search/ Conference Digest - NIPS conference papers ... Tech AI Tools: Literature Review  | Literature Search | Question Answering | Text Summarization Expert AI Tools: Org AI | Expert search | Executive Search, Reviewer Search, Patent Lawyer Search...

Daily paper digest / Conference papers digest / Best paper digest / Topic tracking. In Account enter the subject areas interested. Daily Digest will upload studies based on your interests.

RESEARCH RABBIT

• CITATION-BASED MAPPING: SIMILAR / EARLY / LATER WORKS
• " 100s of millions of academic articles and covers more than 90%+ of materials that can be found in major databases used by academic institutions (such as Scopus, Web of Science, and others) ." See its FAQs page. Search algorithms were borrowed from NIH and Semantic Scholar.

The default “Untitled Collection” will collect your search histories, based on which Research Rabbit will send you recommendations for three types of related results: Similar Works / Earlier Works / Later Works, viewable in graph such as Network, Timeline, First Authors etc.

Zotero integration: importing and exporting between these two apps.

• Example - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality [Login required] Try it to see its Similar Works, Earlier Works and Later Works or other documents.
• Export Results - Findings can be exported in BibTxt, RIS or CSV format.

CITING GENERATIVE AI

• How to cite ChatGPT  [APA] - https://apastyle. apa.org/blog /how-to-cite-chatgpt  
• How to Cite Generative AI  [MLA]  https://style. mla.org /citing-generative-ai/
• Citation Guide - Citing ChatGPT and Other Generative AI (University of Queensland, Australia)
• Next: Dialogues: Insightful Facts >>
• Last Updated: Mar 12, 2024 10:43 AM
• URL: https://tamu.libguides.com/c.php?g=1289555

• Ask a Librarian

Artificial Intelligence (AI)

Ai for systematic review.

• How to Cite AI Generated Content
• Prompt Design
• Resources for Educators
• Purdue AI Resources
• AI and Ethics
• Publisher Policies
• Selected Journals in AI

Various AI tools are invaluable throughout the systematic review or evidence synthesis process. While the consensus acknowledges the significant utility of AI tools across different review stages, it's imperative to grasp their inherent biases and weaknesses. Moreover, ethical considerations such as copyright and intellectual property must be at the forefront.

• Application ChatGPT in conducting systematic reviews and meta-analyses
• Are ChatGPT and large language models “the answer” to bringing us closer to systematic review automation?
• Artificial intelligence in systematic reviews: promising when appropriately used
• Harnessing the power of ChatGPT for automating systematic review process: methodology, case study, limitations, and future directions
• In-depth evaluation of machine learning methods for semi-automating article screening in a systematic review of mechanistic
• Tools to support the automation of systematic reviews: a scoping review
• The use of a large language model to create plain language summaries of evidence reviews in healthcare: A feasibility study
• Using artificial intelligence methods for systematic review in health sciences: A systematic review

AI Tools for Systematic Review

• DistillerSR Securely automate every stage of your literature review to produce evidence-based research faster, more accurately, and more transparently at scale.
• Rayyan A web-tool designed to help researchers working on systematic reviews, scoping reviews and other knowledge synthesis projects, by dramatically speeding up the process of screening and selecting studies.
• RobotReviewer A machine learning system aiming which aims to automate evidence synthesis.
• << Previous: AI Tools
• Next: How to Cite AI Generated Content >>
• Last Edited: Mar 21, 2024 1:34 PM
• URL: https://guides.lib.purdue.edu/ai

Accelerate your dissertation literature review with AI

Become a lateral pioneer.

Get started for free and help craft the future of research.

Early access. No credit card required.

Introduction

Dissertation writing is part of being a graduate student. There are many different ways to organise your research, and several steps to this process . Typically, the literature review is an early chapter in the dissertation, providing an overview of the field of study. It should summarise relevant research papers and other materials in your field, with specific references. To understand how to write a good literature review, we must first understand its purpose. The goals of a literature review are to place your dissertation topic in the context of existing work (this also allows you to acknowledge prior contributions, and avoid accusations of plagiarism), and to set you up to show you are making a new contribution to the field. Since literature review is repetitive, many students find it tedious. While there are some traditional tools and techniques to help, covered below, they tend to be cumbersome and keyword-based. For this reason, we built a better tool for research and literature review, which I describe in the last section. You can see the Lateral tool in action , and how it makes the literature review a lot easier. To sign up to the tool, click here.

1. Different kinds of reading

We can divide the activity of reading for research into three different kinds: 

• Exploratory reading, mostly done in the initial phase;
• Deep reading of highly informative sources; and 
• Broad, targeted skim reading of large collections of books and articles, in order to find specific kinds of information you already know exist.

1.1. Exploratory reading

Initially, a research student will need to read widely in a new field to gain fundamental understanding. In this early stage, the goal is to explore and digest the main ideas in existing research. Traditionally, this phase has been a manual process, but there is a new generation of digital tools to aid in getting a quick overview of your field, and more generally to organise your research . This stage can happen both before and after the research topic or question has been formulated. It is often unstructured and full of serendipitous (“happy accidental”) discovery  — the student’s job is to absorb what they find, rather than to conduct a targeted search for particular information. ‍

Put another way: You don’t know what you’re looking for ahead of time. By the end of this phase, you should be able to sketch a rough map of your field of study.

1.2. Narrow, deep reading

After the exploratory reading phase, you will be able to prioritise the information you read. Now comes the second phase: Deep, reflective reading. In this phase, your focus will narrow to a small number of highly relevant sources — perhaps one or two books, or a handful of articles — which you will read carefully, with the goal of fully understanding important concepts. This is a deliberative style of reading, often accompanied by reflective pauses and significant note taking. If the goal in the first phase was sketching a map of the globe, the goal in this second phase is to decide which cities interest you most, and map them out in colour and detail.

1.3. Broad, targeted reading

You have now sketched a map of your field of study (exploratory reading), and filled in some parts of this map in more detail (narrow, deep reading). I will assume that by this point, you have found a thesis question or research topic, either on your own, or with the help of an advisor. This is often where the literature review begins in earnest. In order to coherently summarise the state of your field, you must review the literature once again, but this time in a more targeted way: You are searching for particular pieces of information that either illustrate existing work, or demonstrate a need for the new approach you will take in your dissertation. For example, 

• You want to find all “methodology” sections in a group of academic articles, and filter for those that have certain key concepts;
• You want to find all paragraphs that discuss product-market fit, inside a group of academic articles.

To return to the map analogy: This is like sketching in the important roads between your favourite cities — you are showing connections between the most important concepts in your field, through targeted information search.

2. Drawbacks of broad targeted reading

The third phase — broad, targeted reading, where you know what kind of information you’re looking for and simply wish to scan a collection of articles or books to find it — is often the most mechanical and time consuming one. Since human brains tend to lose focus in the face of dull repetition, this is also a tedious and error-prone phase for many people. What if you miss something important because you’re on autopilot? Often, students end up speed- or skim reading through large volumes of information to complete the literature review as quickly as possible. With focus and training, this manual approach can be efficient and effective, but it can also mean reduced attention to detail and missed opportunities to discover relevant information. Only half paying attention during this phase can also lead to accidental plagiarism, otherwise known as cryptomnesia: Your brain subconsciously stores a distinctive idea or quote from the existing literature without consciously attributing it to its source reference. Afterwards, you end up falsely, but sincerely believing you created the idea independently, exposing yourself to plagiarism accusations.

3. Existing solutions to speed up literature reviews

Given the drawbacks of manual speed- or skim-reading in the broad reading phase, it’s natural to turn to computer-driven solutions. One popular option is to systematically create a list of search term keywords or key phrases, which can then be combined using boolean operators to broaden results. For example, in researching a study about teenage obesity, one might use the query:

• “BMI” or “obesity” and “adolescents” and not “geriatric”,

to filter for obesity-related articles that do mention adolescents, but don’t mention older adults.

Constructing such lists can help surface many relevant articles, but there are some disadvantages to this strategy:

• These keyword queries are themselves fiddly and time-consuming to create.
• Often what you want to find is whole “chunks” of text — paragraphs or sections, for example — not just keywords.
• Even once you have finished creating your boolean keyword query list, how do you know you haven’t forgotten to include an important search query?

This last point reflects the fact that keyword searching is “fragile” and error-prone: You can miss results that would be relevant — this is known as getting “false negatives” — because your query uses words that are similar, but not identical to words appearing in one or more articles in the library database. For example, the query “sporting excellence” would not match with an article that mentioned only “high performance athletics”.

4. Lateral — a new solution

To make the process of finding specific information in big collections of documents quicker and easier — for example, in a literature review — search, we created the Lateral app , a new kind of AI-driven interface to help you organise, search through and save supporting quotes and information from collections of articles. Using techniques from natural language processing, it understands, out-of-the-box, not only that “sporting excellence” and “high-performance” athletics are very similar phrases, but also that two paragraphs discussing these topics in slightly different language are likely related. Moreover, it also learns to find specific blocks of information, given only a few examples. Want to find all “methodology” sections in a group of articles? Check. How about all paragraphs that mention pharmaceutical applications? We have you covered. If you’re interested, you can sign up today .

5. Final note — novel research alongside the literature review

Some students, to be more efficient, use the literature review process to collect data not just to summarise existing work, but also to support one or more novel theses contained in their research topic. After all, you are reading the literature anyway, so why not take the opportunity to note, for example, relevant facts, quotes and supporting evidence for your thesis? Because Lateral is designed to learn from whatever kind of information you’re seeking, this process also fits naturally into the software’s workflow.

References:

• Is your brain asleep on the job?: https://www.psychologytoday.com/us/blog/prime-your-gray-cells/201107/is-your-brain-asleep-the-job
• Tim Feriss speed reading: https://www.youtube.com/watch?v=ZwEquW_Yij0
• Five biggest reading mistakes: https://www.timeshighereducation.com/blog/five-biggest-reading-mistakes-and-how-avoid-them
• Skim reading can be bad: https://www.inc.com/jeff-steen/why-summaries-skim-reading-might-be-hurting-your-bottom-line.html
• Cryptomnesia: https://en.wikipedia.org/wiki/Cryptomnesia
• Systematic literature review with boolean keywords: https://libguides.library.cqu.edu.au/c.php?g=842872&p=6024187

Lit review youtube intro: https://www.youtube.com/watch?v=bNIG4qLuhJA

Spread the word

There is a better way than Dropbox and Google Drive to do collaborative research

In this blog, I describe the limitations of Dropbox and Google in the space of research, and propose Lateral as the much needed alternative.

Remote group work and the best student collaboration tools

In this blog, I outline some organisational techniques and the best digital collaborative tools for successful student group work.

6 things to consider and organise before writing your dissertation (and how Lateral can help)

I hope the following six things to consider and organise will make the complex dissertation writing more manageable.

Get into flow.

AI for literature reviews

Let ai assist boost your literature review and analysis, how to use ai assist for your literature review.

• Step one: Identify and import your literature
• Step two: Summarize your documents with AI Assist
• Step three: Determine relevance and sort accordingly
• Step four: Reading and rough coding
• Step five: Confirm your initial codings
• Step six: Refine your code system
• Step seven: Analyze your literature

Literature about literature reviews and analysis

Tuesday, September 19, 2023

As you may have noticed, there is a rapid growth in AI-based tools for all types of software packages. We followed this trend by releasing AI Assist – your virtual research assistant that simplifies your qualitative data analysis. In the following, we will present you the tools and functions of AI Assist and how they can facilitate your literature reviews.

Literature reviews are an important step in the data analysis journey of many research projects, but often it is a time-consuming and arduous affair. Whether you are reviewing literature for writing a meta-analysis or for the background section of your thesis, work with MAXQDA! Besides the classic tools of MAXQDA that can facilitate each phase of your literature review, the new tool AI Assist can boost your literature review and analysis in multiple ways.

Year by year, the number of publications grows in almost every field of research – our insights and knowledge likewise. The drawback is that the number of publications might be too high to keep track of the recent developments in your field of research. Consequently, conducting a proper literature review becomes more and more difficult, and the importance of quickly identifying whether a publication is interesting for your research question constantly increases.

Luckily, MAXQDA’s AI Assist tool is here to help. Among others, it can summarize your documents, text segments, and coded segments. But there is more – based on your coded segments AI Assist can generate subcodes suggestions. In the following, we will present you step-by-step instructions on how to use MAXQDA for your literature review and analysis with a special focus on how AI Assist can support you.

Step one of AI for literature reviews: Identify and import your literature

Despite the fact that MAXQDA and AI Assist can facilitate your literature review and analysis in manifold ways, the best advice is to carefully plan your literature review and analysis. Think about the purpose of your literature review and the questions you want to answer. Develop a search strategy which includes, but is not limited to, deciding on literature databases, search terms, and practical and methodological criteria for selecting high-quality scientific literature. Then start your literature review and analysis by searching the identified databases. Before downloading the PDFs and/or bibliographic information (RIS), briefly scan the search results for relevance by reading the title, keywords and abstract. If you find the publication interesting, download the PDF, and let AI Assist help you determining whether the publication falls within the narrower area of your research question.

MAXQDA’s import tab offers import options dedicated to different data types, such as bibliographic data (in RIS file format) and PDF documents. To import the selected literature, just click on the corresponding button, select the data you want to import, and click okay. Alternatively, you can import data simply by drag-and-dropping the data files from your Windows Explorer/Mac Finder window. If you import full texts and the corresponding bibliographic data, MAXQDA automatically connects the full text to the literature entry with an internal link.

Step two of AI for literature reviews: Summarize your documents with AI Assist

Now that you have imported all publications that might be interesting for your research question, it is time to explore whether they are indeed relevant for your literature review and analysis. Before the release of AI Assist, this step typically took a lot of time as you had to go through each paper individually. With the release of AI Assist, MAXQDA can accelerate this step with AI-generated summaries of your publications. For example, you can create AI-generated summaries either for the entire publication or for each chapter (e.g. Introduction, Methods, Results, and so on) individually and base your decision about a paper’s relevance on these summaries. Each AI-generated summary is stored in a memo that is attached to the underlying document or text segment, respectively.

Summarizing text segments with AI Assist just takes a few clicks. Simply highlight a text segment in the Document Browser and choose AI Assist from the context menu. Adjust the settings to your needs and let OpenAI do the work for you. To view and edit the summary, double-click on the yellow memo icon attached to the summarized text passage.

Adjust settings for summarizing text with AI Assist for literature reviews

Step three of AI for literature reviews: Determine relevance and sort accordingly

Instead of reading the entire paper, you can use the AI-generated summaries to determine whether a publication falls within the narrower area of your research question. To do so, it might be helpful to view all memos containing summaries of a specific publication at once. Of course, this is possible with MAXQDA. Go to the Memo tab, click on (In-)document Memos, and click on the publication’s name to view only the AI-generated summaries related to this document. It is important to note that AI-generated summaries are not perfect yet. Therefore, it is advisable to read the entire paper in cases where you have doubts or can’t decide whether the publication is relevant.

Depending on the number of publications in your MAXQDA project, you might want to sort your documents in document groups, for example, based on the relevance for your research question or the topics discussed in the paper. You can easily create a new Document group by clicking on the respective icon in the Document System window. Documents can be added simply via drag-and-drop. Alternatively, you can create Document Sets which are especially helpful when you want to sort your documents by more than one domain (e.g. by relevance and methodology used).

Sort documents in document groups according to their relevance using AI for literature reviews

Step four of AI for literature reviews: Reading and rough coding

Now that you have identified the publications important to your project, it is time to go through the documents. Although, AI Assist can support you at multiple stages of your literature review, it can’t replace the researcher. As a researcher, you still need a deep understanding of your material, analysis methods, and the software you use for analysis. As AI-generated summaries are not perfect yet, you might want to improve the summaries, if necessary, or add information that you consider especially important, e.g. participants’ demographics.

In a next step, it is time to create and apply some codes to the data. A code can be described as a label used to name phenomena in a text or an image. Depending on your approach, you might already have codes in mind (deductive coding) or you plan to generate codes on the basis of the data (inductive coding). No matter your approach – you can use MAXQDA’s advanced tools for coding. In many cases it is best, to start your first round of coding with rather rough codes that you can refine in a later step using the help of AI Assist. You can create codes in the Code System window by clicking on the plus-icon or in the Document Browser by highlighting a text segment via the context menu or the corresponding icons. A code can be applied to the data via drag-and-drop.

Reading and rough coding for AI for literature reviews

Step five of AI for literature reviews: Confirm your initial codings

Though AI Assist can’t validate your codings like a second researcher using intercoder agreement, AI Assist’s Code Summaries can help you to identify whether you have applied the code as intended. The AI-generated Code Summary is a summary of the content of all text segments coded with the corresponing code. This summary might give you an idea of how you have applied the code and if the coded text segments indeed contain what you had in mind when creating the code.

To create a summary of coded segments with AI Assist, simply right-click the code of interest in the Code System and choose AI Assist > Code Summary from the context menu. Adjust language and the summary length to your needs and let AI Assist do the summary for you. As for document summaries, the summary will be stored in a memo which is placed next to the code in the Code System. If the summary doesn’t match your code definition, you might want to review the coded segments and adjust your codings accordingly. By double-clicking on a code, you open the Overview of Coded Segments – a table perfectly suited to go through the coded segments and adjust or remove the codings.

Confirm your initial codings with AI Assist’s Code Summary for literature reviews

Step six of AI for literature reviews: Refine your code system

In case you have applied rather rough codes to your data, your code definitions are probably too broad for you to make sense of the data. Depending on your goals, you might wish to refine these rather broad codes into more precise sub-codes. Again, you can use AI Assist’s power to support this step of your literature review. AI Assist analyzes the text and suggests subcodes while leaving the decision on whether you want to create the suggested sub-codes up to you.

To create AI-generated subcode suggestions, open the context menu of a code and choose AI Assist > Suggest Subcodes. Besides selecting a language, you can ask AI Assist to include examples for each subcode as a bullet list. Like the AI-generated summaries, the code suggestions are stored in the code’s memo. If you are satisfied with the code suggestions, you can create and apply them to your data. Alternatively, you can use the AI-generated code suggestions to confirm the subcodes that you have created.

Use AI Assist’s Suggest Subcodes function to refine your code system for your literature reviews

Step seven of AI for literature reviews: Analyze your literature

Now that you have coded your literature, it’s time to analyze the material with MAXQDA. Although you can use plenty of MAXQDA’s tools and functions even when the material is not coded, other tools require coded segments to be applicable. MAXQDA offers plenty of tools for qualitative data analysis, impossible to mention all. Among others, MAXQDA’s Overview and Summary Tables are useful for aggregating your data. With MAXQDA Visualization Tools you can quickly and easily create stunning visualizations of your data, and with MAXQDA’s Questions-Themes-Theories tool you have a place to synthesize your results and write up a literature review or report.

You can find more information and ideas for conducting a literature review with MAXQDA, here:

Learn more about literature reviews

For information about AI Assist and how to Activate AI Assist, visit:

Learn more about AI Assist

We offer a variety of free learning materials to help you get started with your literature review. Check out our Getting Started Guide to get a quick overview of MAXQDA and step-by-step instructions on setting up your software and creating your first project with your brand new QDA software. In addition, the free Literature Reviews Guide explains how to conduct a literature review with MAXQDA in more detail.

Getting Started with MAXQDA

Literature Reviews with MAXQDA

MAXQDA Newsletter

Our research and analysis tips, straight to your inbox.

• By submitting the form I accept the Privacy Policy.

RAxter is now Enago Read! Enjoy the same licensing and pricing with enhanced capabilities. No action required for existing customers.

Your all in one AI-powered Reading Assistant

A Reading Space to Ideate, Create Knowledge, and Collaborate on Your Research

• Smartly organize your research
• Receive recommendations that cannot be ignored
• Collaborate with your team to read, discuss, and share knowledge

From Surface-Level Exploration to Critical Reading - All in one Place!

Fine-tune your literature search.

Our AI-powered reading assistant saves time spent on the exploration of relevant resources and allows you to focus more on reading.

Select phrases or specific sections and explore more research papers related to the core aspects of your selections. Pin the useful ones for future references.

Our platform brings you the latest research related to your and project work.

Speed up your literature review

Quickly generate a summary of key sections of any paper with our summarizer.

Make informed decisions about which papers are relevant, and where to invest your time in further reading.

Get key insights from the paper, quickly comprehend the paper’s unique approach, and recall the key points.

Bring order to your research projects

Organize your reading lists into different projects and maintain the context of your research.

Quickly sort items into collections and tag or filter them according to keywords and color codes.

Experience the power of sharing by finding all the shared literature at one place.

Decode papers effortlessly for faster comprehension

Highlight what is important so that you can retrieve it faster next time.

Select any text in the paper and ask Copilot to explain it to help you get a deeper understanding.

Ask questions and follow-ups from AI-powered Copilot.

Collaborate to read with your team, professors, or students

Share and discuss literature and drafts with your study group, colleagues, experts, and advisors. Recommend valuable resources and help each other for better understanding.

Work in shared projects efficiently and improve visibility within your study group or lab members.

Keep track of your team's progress by being constantly connected and engaging in active knowledge transfer by requesting full access to relevant papers and drafts.

Find papers from across the world's largest repositories

Testimonials

Privacy and security of your research data are integral to our mission..

Everything you add or create on Enago Read is private by default. It is visible if and when you share it with other users.

You can put Creative Commons license on original drafts to protect your IP. For shared files, Enago Read always maintains a copy in case of deletion by collaborators or revoked access.

We use state-of-the-art security protocols and algorithms including MD5 Encryption, SSL, and HTTPS to secure your data.

AI Research Tools for Literature Reviews

• Consider the Ethics

Director, Teaching & Learning

This guide is intended to introduce AI-assisted tools for completing literature reviews. 

Disclaimer: 

• This guide is not intended to cover every step of the literature review. To understand the purpose and process behind literature reviews, see  Literature Reviews: An Overview for Graduate Students (9:35 minute Video, from NCState) and  Learn how to write a review of literature (Steps and Examples from UW-Madison Writing Center). 
• There are many, many more tools not included in this guide. Tools without the option of being freely available are not included. 
• Use with caution and critical thinking. These tools are new and still in development. They are subject to bias. Though most tools listed in this guide rely on citation metadata and Natural Language Understanding/Machine Learning (rather than generated content), "hallucinations" or made-up references may still occur. Always double-check! 

Attribution

Organization for the Guide was inspired by Prof. Niels Van Quaquebeke's AI Tools for Research Workflow in Academia , which is licensed under the Creative Commons License CC BY 4.0 . Some tool descriptions were also adapted from this work, while others were taken directly from the product websites. 

Introductory Slides

• Next: Discover >>
• Last Updated: Feb 7, 2024 1:20 PM
• URL: https://guides.library.txstate.edu/LitReviewAI

A free, AI-powered research tool for scientific literature

• Hideo Hosono
• Game Theory
• Mixed Media

New & Improved API for Developers

Introducing semantic reader in beta.

Stay Connected With Semantic Scholar Sign Up What Is Semantic Scholar? Semantic Scholar is a free, AI-powered research tool for scientific literature, based at the Allen Institute for AI.

Something went wrong when searching for seed articles. Please try again soon.

No articles were found for that search term.

Author, year The title of the article goes here

LITERATURE REVIEW SOFTWARE FOR BETTER RESEARCH

“This tool really helped me to create good bibtex references for my research papers”

Ali Mohammed-Djafari

Director of Research at LSS-CNRS, France

“Any researcher could use it! The paper recommendations are great for anyone and everyone”

Swansea University, Wales

“As a student just venturing into the world of lit reviews, this is a tool that is outstanding and helping me find deeper results for my work.”

Franklin Jeffers

South Oregon University, USA

“One of the 3 most promising tools that (1) do not solely rely on keywords, (2) does nice visualizations, (3) is easy to use”

Singapore Management University

“Incredibly useful tool to get to know more literature, and to gain insight in existing research”

KU Leuven, Belgium

“Seeing my literature list as a network enhances my thinking process!”

Katholieke Universiteit Leuven, Belgium

“I can’t live without you anymore! I also recommend you to my students.”

Professor at The Chinese University of Hong Kong

“This has helped me so much in researching the literature. Currently, I am beginning to investigate new fields and this has helped me hugely”

Aran Warren

Canterbury University, NZ

“It's nice to get a quick overview of related literature. Really easy to use, and it helps getting on top of the often complicated structures of referencing”

Christoph Ludwig

Technische Universität Dresden, Germany

“Litmaps is extremely helpful with my research. It helps me organize each one of my projects and see how they relate to each other, as well as to keep up to date on publications done in my field”

Daniel Fuller

Clarkson University, USA

“Litmaps is a game changer for finding novel literature... it has been invaluable for my productivity.... I also got my PhD student to use it and they also found it invaluable, finding several gaps they missed”

Varun Venkatesh

Austin Health, Australia

Mastering Literature Reviews with Litmaps

Analyze research papers at superhuman speed

Search for research papers, get one sentence abstract summaries, select relevant papers and search for more like them, extract details from papers into an organized table.

Find themes and concepts across many papers

Don't just take our word for it.

Tons of features to speed up your research

Upload your own pdfs, orient with a quick summary, view sources for every answer, ask questions to papers, research for the machine intelligence age, pick a plan that's right for you, get in touch, enterprise and institutions, custom pricing, common questions. great answers., how do researchers use elicit.

Over 800,000 researchers have tried Elicit already. Researchers commonly use Elicit to:

• Speed up literature review
• Find papers they couldn’t find elsewhere
• Automate systematic reviews and meta-analyses
• Learn about a new domain

Elicit tends to work best for empirical domains that involve experiments and concrete results. This type of research is common in biomedicine and machine learning.

What is Elicit not a good fit for?

Elicit does not currently answer questions or surface information that is not written about in an academic paper. It tends to work less well for identifying facts (e.g. “How many cars were sold in Malaysia last year?”) and theoretical or non-empirical domains.

What types of data can Elicit search over?

Elicit searches across 200 million academic papers from the Semantic Scholar corpus, which covers all academic disciplines. When you extract data from papers in Elicit, Elicit will use the full text if available or the abstract if not.

How accurate are the answers in Elicit?

A good rule of thumb is to assume that around 90% of the information you see in Elicit is accurate. While we do our best to increase accuracy without skyrocketing costs, it’s very important for you to check the work in Elicit closely. We try to make this easier for you by identifying all of the sources for information generated with language models.

What is Elicit Plus?

Elicit Plus is Elicit's subscription offering, which comes with a set of features, as well as monthly credits. On Elicit Plus, you may use up to 12,000 credits a month. Unused monthly credits do not carry forward into the next month. Plus subscriptions auto-renew every month.

What are credits?

Elicit uses a credit system to pay for the costs of running our app. When you run workflows and add columns to tables it will cost you credits. When you sign up you get 5,000 credits to use. Once those run out, you'll need to subscribe to Elicit Plus to get more. Credits are non-transferable.

How can you get in contact with the team?

Please email us at [email protected] or post in our Slack community if you have feedback or general comments! We log and incorporate all user comments. If you have a problem, please email [email protected] and we will try to help you as soon as possible.

What happens to papers uploaded to Elicit?

When you upload papers to analyze in Elicit, those papers will remain private to you and will not be shared with anyone else.

How accurate is Elicit?

Training our models on specific tasks, searching over academic papers, making it easy to double-check answers, save time, think more. try elicit for free..

Help | Advanced Search

Computer Science > Digital Libraries

Title: ai literature review suite.

Abstract: The process of conducting literature reviews is often time-consuming and labor-intensive. To streamline this process, I present an AI Literature Review Suite that integrates several functionalities to provide a comprehensive literature review. This tool leverages the power of open access science, large language models (LLMs) and natural language processing to enable the searching, downloading, and organizing of PDF files, as well as extracting content from articles. Semantic search queries are used for data retrieval, while text embeddings and summarization using LLMs present succinct literature reviews. Interaction with PDFs is enhanced through a user-friendly graphical user interface (GUI). The suite also features integrated programs for bibliographic organization, interaction and query, and literature review summaries. This tool presents a robust solution to automate and optimize the process of literature review in academic and industrial research.

Submission history

Access paper:.

• Download PDF
• Other Formats

References & Citations

• Google Scholar
• Semantic Scholar

BibTeX formatted citation

Bibliographic and Citation Tools

Code, data and media associated with this article, recommenders and search tools.

• Institution

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, generate accurate citations for free.

• Knowledge Base

Methodology

• How to Write a Literature Review | Guide, Examples, & Templates

How to Write a Literature Review | Guide, Examples, & Templates

Published on January 2, 2023 by Shona McCombes . Revised on September 11, 2023.

What is a literature review? A literature review is a survey of scholarly sources on a specific topic. It provides an overview of current knowledge, allowing you to identify relevant theories, methods, and gaps in the existing research that you can later apply to your paper, thesis, or dissertation topic .

There are five key steps to writing a literature review:

• Search for relevant literature
• Evaluate sources
• Identify themes, debates, and gaps
• Outline the structure
• Write your literature review

A good literature review doesn’t just summarize sources—it analyzes, synthesizes , and critically evaluates to give a clear picture of the state of knowledge on the subject.

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

What is the purpose of a literature review, examples of literature reviews, step 1 – search for relevant literature, step 2 – evaluate and select sources, step 3 – identify themes, debates, and gaps, step 4 – outline your literature review’s structure, step 5 – write your literature review, free lecture slides, other interesting articles, frequently asked questions, introduction.

• Quick Run-through
• Step 1 & 2

When you write a thesis , dissertation , or research paper , you will likely have to conduct a literature review to situate your research within existing knowledge. The literature review gives you a chance to:

• Demonstrate your familiarity with the topic and its scholarly context
• Develop a theoretical framework and methodology for your research
• Position your work in relation to other researchers and theorists
• Show how your research addresses a gap or contributes to a debate
• Evaluate the current state of research and demonstrate your knowledge of the scholarly debates around your topic.

Writing literature reviews is a particularly important skill if you want to apply for graduate school or pursue a career in research. We’ve written a step-by-step guide that you can follow below.

Prevent plagiarism. Run a free check.

Writing literature reviews can be quite challenging! A good starting point could be to look at some examples, depending on what kind of literature review you’d like to write.

• Example literature review #1: “Why Do People Migrate? A Review of the Theoretical Literature” ( Theoretical literature review about the development of economic migration theory from the 1950s to today.)
• Example literature review #2: “Literature review as a research methodology: An overview and guidelines” ( Methodological literature review about interdisciplinary knowledge acquisition and production.)
• Example literature review #3: “The Use of Technology in English Language Learning: A Literature Review” ( Thematic literature review about the effects of technology on language acquisition.)
• Example literature review #4: “Learners’ Listening Comprehension Difficulties in English Language Learning: A Literature Review” ( Chronological literature review about how the concept of listening skills has changed over time.)

You can also check out our templates with literature review examples and sample outlines at the links below.

Download Word doc Download Google doc

Before you begin searching for literature, you need a clearly defined topic .

If you are writing the literature review section of a dissertation or research paper, you will search for literature related to your research problem and questions .

Make a list of keywords

Start by creating a list of keywords related to your research question. Include each of the key concepts or variables you’re interested in, and list any synonyms and related terms. You can add to this list as you discover new keywords in the process of your literature search.

• Social media, Facebook, Instagram, Twitter, Snapchat, TikTok
• Body image, self-perception, self-esteem, mental health
• Generation Z, teenagers, adolescents, youth

Search for relevant sources

Use your keywords to begin searching for sources. Some useful databases to search for journals and articles include:

• Your university’s library catalogue
• Google Scholar
• Project Muse (humanities and social sciences)
• Medline (life sciences and biomedicine)
• EconLit (economics)
• Inspec (physics, engineering and computer science)

You can also use boolean operators to help narrow down your search.

Make sure to read the abstract to find out whether an article is relevant to your question. When you find a useful book or article, you can check the bibliography to find other relevant sources.

You likely won’t be able to read absolutely everything that has been written on your topic, so it will be necessary to evaluate which sources are most relevant to your research question.

For each publication, ask yourself:

• What question or problem is the author addressing?
• What are the key concepts and how are they defined?
• What are the key theories, models, and methods?
• Does the research use established frameworks or take an innovative approach?
• What are the results and conclusions of the study?
• How does the publication relate to other literature in the field? Does it confirm, add to, or challenge established knowledge?
• What are the strengths and weaknesses of the research?

Make sure the sources you use are credible , and make sure you read any landmark studies and major theories in your field of research.

You can use our template to summarize and evaluate sources you’re thinking about using. Click on either button below to download.

Take notes and cite your sources

As you read, you should also begin the writing process. Take notes that you can later incorporate into the text of your literature review.

It is important to keep track of your sources with citations to avoid plagiarism . It can be helpful to make an annotated bibliography , where you compile full citation information and write a paragraph of summary and analysis for each source. This helps you remember what you read and saves time later in the process.

To begin organizing your literature review’s argument and structure, be sure you understand the connections and relationships between the sources you’ve read. Based on your reading and notes, you can look for:

• Trends and patterns (in theory, method or results): do certain approaches become more or less popular over time?
• Themes: what questions or concepts recur across the literature?
• Debates, conflicts and contradictions: where do sources disagree?
• Pivotal publications: are there any influential theories or studies that changed the direction of the field?
• Gaps: what is missing from the literature? Are there weaknesses that need to be addressed?

This step will help you work out the structure of your literature review and (if applicable) show how your own research will contribute to existing knowledge.

• Most research has focused on young women.
• There is an increasing interest in the visual aspects of social media.
• But there is still a lack of robust research on highly visual platforms like Instagram and Snapchat—this is a gap that you could address in your own research.

There are various approaches to organizing the body of a literature review. Depending on the length of your literature review, you can combine several of these strategies (for example, your overall structure might be thematic, but each theme is discussed chronologically).

Chronological

The simplest approach is to trace the development of the topic over time. However, if you choose this strategy, be careful to avoid simply listing and summarizing sources in order.

Try to analyze patterns, turning points and key debates that have shaped the direction of the field. Give your interpretation of how and why certain developments occurred.

If you have found some recurring central themes, you can organize your literature review into subsections that address different aspects of the topic.

For example, if you are reviewing literature about inequalities in migrant health outcomes, key themes might include healthcare policy, language barriers, cultural attitudes, legal status, and economic access.

Methodological

If you draw your sources from different disciplines or fields that use a variety of research methods , you might want to compare the results and conclusions that emerge from different approaches. For example:

• Look at what results have emerged in qualitative versus quantitative research
• Discuss how the topic has been approached by empirical versus theoretical scholarship
• Divide the literature into sociological, historical, and cultural sources

Theoretical

A literature review is often the foundation for a theoretical framework . You can use it to discuss various theories, models, and definitions of key concepts.

You might argue for the relevance of a specific theoretical approach, or combine various theoretical concepts to create a framework for your research.

Like any other academic text , your literature review should have an introduction , a main body, and a conclusion . What you include in each depends on the objective of your literature review.

The introduction should clearly establish the focus and purpose of the literature review.

Depending on the length of your literature review, you might want to divide the body into subsections. You can use a subheading for each theme, time period, or methodological approach.

As you write, you can follow these tips:

• Summarize and synthesize: give an overview of the main points of each source and combine them into a coherent whole
• Analyze and interpret: don’t just paraphrase other researchers — add your own interpretations where possible, discussing the significance of findings in relation to the literature as a whole
• Critically evaluate: mention the strengths and weaknesses of your sources
• Write in well-structured paragraphs: use transition words and topic sentences to draw connections, comparisons and contrasts

In the conclusion, you should summarize the key findings you have taken from the literature and emphasize their significance.

When you’ve finished writing and revising your literature review, don’t forget to proofread thoroughly before submitting. Not a language expert? Check out Scribbr’s professional proofreading services !

This article has been adapted into lecture slides that you can use to teach your students about writing a literature review.

Scribbr slides are free to use, customize, and distribute for educational purposes.

Open Google Slides Download PowerPoint

If you want to know more about the research process , methodology , research bias , or statistics , make sure to check out some of our other articles with explanations and examples.

• Sampling methods
• Simple random sampling
• Stratified sampling
• Cluster sampling
• Likert scales
• Reproducibility

 Statistics

• Null hypothesis
• Statistical power
• Probability distribution
• Effect size
• Poisson distribution

Research bias

• Optimism bias
• Cognitive bias
• Implicit bias
• Hawthorne effect
• Anchoring bias
• Explicit bias

A literature review is a survey of scholarly sources (such as books, journal articles, and theses) related to a specific topic or research question .

It is often written as part of a thesis, dissertation , or research paper , in order to situate your work in relation to existing knowledge.

There are several reasons to conduct a literature review at the beginning of a research project:

• To familiarize yourself with the current state of knowledge on your topic
• To ensure that you’re not just repeating what others have already done
• To identify gaps in knowledge and unresolved problems that your research can address
• To develop your theoretical framework and methodology
• To provide an overview of the key findings and debates on the topic

Writing the literature review shows your reader how your work relates to existing research and what new insights it will contribute.

The literature review usually comes near the beginning of your thesis or dissertation . After the introduction , it grounds your research in a scholarly field and leads directly to your theoretical framework or methodology .

A literature review is a survey of credible sources on a topic, often used in dissertations , theses, and research papers . Literature reviews give an overview of knowledge on a subject, helping you identify relevant theories and methods, as well as gaps in existing research. Literature reviews are set up similarly to other  academic texts , with an introduction , a main body, and a conclusion .

An  annotated bibliography is a list of  source references that has a short description (called an annotation ) for each of the sources. It is often assigned as part of the research process for a  paper .  

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the “Cite this Scribbr article” button to automatically add the citation to our free Citation Generator.

McCombes, S. (2023, September 11). How to Write a Literature Review | Guide, Examples, & Templates. Scribbr. Retrieved March 20, 2024, from https://www.scribbr.com/dissertation/literature-review/

Is this article helpful?

Shona McCombes

Other students also liked, what is a theoretical framework | guide to organizing, what is a research methodology | steps & tips, how to write a research proposal | examples & templates, unlimited academic ai-proofreading.

✔ Document error-free in 5minutes ✔ Unlimited document corrections ✔ Specialized in correcting academic texts

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• NATURE INDEX
• 20 March 2024

Is AI ready to mass-produce lay summaries of research articles?

• Kamal Nahas 0

Kamal Nahas is a freelance science journalist based in Oxford, UK

You can also search for this author in PubMed   Google Scholar

Generative AI might be a powerful tool in making research more accessible for scientists and the broader public alike. Credit: Getty

Thinking back to the early days of her PhD programme, Esther Osarfo-Mensah recalls struggling to keep up with the literature. “Sometimes, the wording or the way the information is presented actually makes it quite a task to get through a paper,” says the biophysicist at University College London. Lay summaries could be a time-saving solution. Short synopses of research articles written in plain language could help readers to decide which papers to focus on — but they aren’t common in scientific publishing. Now, the buzz around artificial intelligence (AI) has pushed software engineers to develop platforms that can mass produce these synopses.

Scientists are drawn to AI tools because they excel at crafting text in accessible language, and they might even produce clearer lay summaries than those written by people. A study 1 released last year looked at lay summaries published in one journal and found that those created by people were less readable than were the original abstracts — potentially because some researchers struggle to replace jargon with plain language or to decide which facts to include when condensing the information into a few lines.

AI lay-summary platforms come in a variety of forms (see ‘AI lay-summary tools’). Some allow researchers to import a paper and generate a summary; others are built into web servers, such as the bioRxiv preprint database.

AI lay-summary tools

Several AI resources have been developed to help readers glean information about research articles quickly. They offer different perks. Here are a few examples and how they work:

- SciSummary: This tool parses the sections of a paper to extract the key points and then runs those through the general-purpose large language model GPT-3.5 to transform them into a short summary written in plain language. Max Heckel, the tool’s founder, says it incorporates multimedia into the summary, too: “If it determines that a particular section of the summary is relevant to a figure or table, it will actually show that table or figure in line.”

- Scholarcy: This technology takes a different approach. Its founder, Phil Gooch, based in London, says the tool was trained on 25,000 papers to identify sentences containing verb phrases such as “has been shown to” that often carry key information about the study. It then uses a mixture of custom and open-source large language models to paraphrase those sentences in plain text. “You can actually create ten different types of summaries,” he adds, including one that lays out how the paper is related to previous publications.

- SciSpace: This tool was trained on a repository of more than 280 million data sets, including papers that people had manually annotated, to extract key information from articles. It uses a mixture of proprietary fine-tuned models and GPT-3.5 to craft the summary, says the company’s chief executive, Saikiran Chandha, based in San Francisco, California. “A user can ask questions on top of these summaries to further dig into the paper,” he notes, adding that the company plans to develop audio summaries that people can tune into on the go.

Benefits and drawbacks

Mass-produced lay summaries could yield a trove of benefits. Beyond helping scientists to speed-read the literature, the synopses can be disseminated to people with different levels of expertise, including members of the public. Osarfo-Mensah adds that AI summaries might also aid people who struggle with English. “Some people hide behind jargon because they don’t necessarily feel comfortable trying to explain it,” she says, but AI could help them to rework technical phrases. Max Heckel is the founder of SciSummary, a company in Columbus, Ohio, that offers a tool that allows users to import a paper to be summarized. The tool can also translate summaries into other languages, and is gaining popularity in Indonesia and Turkey, he says, arguing that it could topple language barriers and make science more accessible.

Despite these strides, some scientists feel that improvements are needed before we can rely on AI to describe studies accurately.

Will Ratcliff, an evolutionary biologist at the Georgia Institute of Technology in Atlanta, argues that no tool can produce better text than can professional writers. Although researchers have different writing abilities, he invariably prefers reading scientific material produced by study authors over those generated by AI. “I like to see what the authors wrote. They put craft into it, and I find their abstract to be more informative,” he says.

Is ChatGPT making scientists hyper-productive? The highs and lows of using AI

Nana Mensah, a PhD student in computational biology at the Francis Crick Institute in London, adds that, unlike AI, people tend to craft a narrative when writing lay summaries, helping readers to understand the motivations behind each step of the study. He says, however, that one advantage of AI platforms is that they can write summaries at different reading levels, potentially broadening the audience. In his experience, however, these synopses might still include jargon that can confuse readers without specialist knowledge.

AI tools might even struggle to turn technical language into lay versions at all. Osarfo-Mensah works in biophysics, a field with many intricate parameters and equations. She found that an AI summary of one of her research articles excluded information from a whole section. If researchers were looking for a paper with those details and consulted the AI summary, they might abandon her paper and look for other work.

Andy Shepherd, scientific director at global technology company Envision Pharma Group in Horsham, UK, has in his spare time compared the performances of several AI tools to see how often they introduce blunders. He used eight text generators, including general ones and some that had been optimized to produce lay summaries. He then asked people with different backgrounds, such as health-care professionals and the public, to assess how clear, readable and useful lay summaries were for two papers.

“All of the platforms produced something that was coherent and read like a reasonable study, but a few of them introduced errors, and two of them actively reversed the conclusion of the paper,” he says. It’s easy for AI tools to make this mistake by, for instance, omitting the word ‘not’ in a sentence, he explains. Ratcliff cautions that AI summaries should be viewed as a tool’s “best guess” of what a paper is about, stressing that it can’t check facts.

Broader readership

The risk of AI summaries introducing errors is one concern among many. Another is that one benefit of such summaries — that they can help to share research more widely among the public — could also have drawbacks. The AI summaries posted alongside bioRxiv preprints, research articles that have yet to undergo peer review, are tailored to different levels of reader expertise, including that of the public. Osarfo-Mensah supports the effort to widen the reach of these works. “The public should feel more involved in science and feel like they have a stake in it, because at the end of the day, science isn’t done in a vacuum,” she says.

But others point out that this comes with the risk of making unreviewed and inaccurate research more accessible. Mensah says that academics “will be able to treat the article with the sort of caution that’s required”, but he isn’t sure that members of the public will always understand when a summary refers to unreviewed work. Lay summaries of preprints should come with a “hazard warning” informing the reader upfront that the material has yet to be reviewed, says Shepherd.

Why scientists trust AI too much — and what to do about it

“We agree entirely that preprints must be understood as not peer-reviewed when posted,” says John Inglis, co-founder of bioRxiv, who is based at Cold Spring Harbor Laboratory in New York. He notes that such a disclaimer can be found on the homepage of each preprint, and if a member of the public navigates to a preprint through a web search, they are first directed to the homepage displaying this disclaimer before they can access the summary. But the warning labels are not integrated into the summaries, so there is a risk that these could be shared on social media without the disclaimer. Inglis says bioRxiv is working with its partner ScienceCast, whose technology produces the synopses, on adding a note to each summary to negate this risk.

As is the case for many other nascent generative-AI technologies, humans are still working out the messaging that might be needed to ensure users are given adequate context. But if AI lay-summary tools can successfully mitigate these and other challenges, they might become a staple of scientific publishing.

doi: https://doi.org/10.1038/d41586-024-00865-4

Wen, J. & Yi, L. Scientometrics 128 , 5791–5800 (2023).

Article   Google Scholar  

Download references

Related Articles

How research managers are using AI to get ahead

• Peer review
• Research management

Peer-replication model aims to address science’s ‘reproducibility crisis’

Nature Index 13 MAR 24

Submitting papers to several journals at once

Correspondence 28 NOV 23

What reproducibility crisis? New research protocol yields ultra-high replication rate

News 09 NOV 23

Numbers highlight US dominance in clinical research

Embrace AI to break down barriers in publishing for people who aren’t fluent in English

Correspondence 12 MAR 24

Is the Mars rover’s rock collection worth $11 billion?

News 19 MAR 24

People, passion, publishable: an early-career researcher’s checklist for prioritizing projects

Career Column 15 MAR 24

Recruitment of Talent Positions at Shengjing Hospital of China Medical University

Call for top experts and scholars in the field of science and technology.

Shenyang, Liaoning, China

Shengjing Hospital of China Medical University

Assistant Professor in Plant Biology

The Plant Science Program in the Biological and Environmental Science and Engineering (BESE) Division at King Abdullah University of Science and Te...

Saudi Arabia (SA)

King Abdullah University of Science and Technology

Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Warmly Welcomes Talents Abroad

“Qiushi” Distinguished Scholar, Zhejiang University, including Professor and Physician

No. 3, Qingchun East Road, Hangzhou, Zhejiang (CN)

Sir Run Run Shaw Hospital Affiliated with Zhejiang University School of Medicine

Postdoctoral Associate

Our laboratory at the Washington University in St. Louis is seeking a postdoctoral experimental biologist to study urogenital diseases and cancer.

Saint Louis, Missouri

Washington University School of Medicine Department of Medicine

Recruitment of Global Talent at the Institute of Zoology, Chinese Academy of Sciences (IOZ, CAS)

The Institute of Zoology (IOZ), Chinese Academy of Sciences (CAS), is seeking global talents around the world.

Beijing, China

Institute of Zoology, Chinese Academy of Sciences (IOZ, CAS)

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Empowering education development through AIGC: A systematic literature review

• Published: 29 February 2024

Cite this article

• Xiaojiao Chen 1 ,
• Zhebing Hu 2 &
• Chengliang Wang   ORCID: orcid.org/0000-0003-2208-3508 3  

534 Accesses

Explore all metrics

As an exemplary representative of AIGC products, ChatGPT has ushered in new possibilities for the field of education. Leveraging its robust text generation and comprehension capabilities, it has had a revolutionary impact on pedagogy, learning experiences, personalized education and other aspects. However, to date, there has been no comprehensive review of AIGC technology’s application in education. In light of this gap, this study employs a systematic literature review and selects 134 relevant publications on AIGC’s educational application from 4 databases: EBSCO, EI Compendex, Scopus, and Web of Science. The study aims to explore the macro development status and future trends in AIGC’s educational application. The following findings emerge: 1) In the AIGC’s educational application field, the United States is the most active country. Theoretical research dominates the research types in this domain; 2) Research on AIGC’s educational application is primarily published in journals and academic conferences in the fields of educational technology and medicine; 3) Research topics primarily focus on five themes: AIGC technology performance assessment, AIGC technology instructional application, AIGC technology enhancing learning outcomes, AIGC technology educational application’s Advantages and Disadvantages analysis, and AIGC technology educational application prospects. 4) Through Grounded Theory, the study delves into the core advantages and potential risks of AIGC’s educational application, deconstructing the scenarios and logic of AIGC’s educational application. 5) Based on a review of existing literature, the study provides valuable future agendas from both theoretical and practical application perspectives. Discussing the future research agenda contributes to clarifying key issues related to the integration of AI and education, promoting more intelligent, effective, and sustainable educational methods and tools, which is of great significance for advancing innovation and development in the field of education.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Data availability

The datasets (Coding results) generated during and/or analysed during the current study are available from the corresponding author on reasonable request.

Abdelghani, R., Wang, Y. H., Yuan, X., Wang, T., Lucas, P., Sauzéon, H., & Oudeyer, P. Y. (2023). Gpt-3-driven pedagogical agents to train children’s curious question-asking skills. International Journal of Artificial Intelligence in Education , 1–36. https://doi.org/10.1007/s40593-023-00340-7

Abdulai, A. F., & Hung, L. (2023). Will ChatGPT undermine ethical values in nursing education, research, and practice. Nursing Inquiry . e12556–e12556. https://doi.org/10.1111/nin.12556

Ahmed, S. K. (2023). The Impact of ChatGPT on the Nursing Profession: Revolutionizing Patient Care and Education. Annals of Biomedical Engineering , 1–2. https://doi.org/10.1007/s10439-023-03262-6

Albeshri, A., & Thayananthan, V. (2018). Analytical techniques for decision making on information security for big data breaches. International Journal of Information Technology & Decision Making, 17 (02), 527–545. https://doi.org/10.1142/S0219622017500432

Article   Google Scholar  

Allen, B., Dreyer, K., Stibolt Jr, R., Agarwal, S., Coombs, L., Treml, C., ... & Wald, C. (2021). Evaluation and real-world performance monitoring of artificial intelligence models in clinical practice: Try it, buy it, check it. Journal of the American College of Radiology , 18 (11), 1489–1496. https://doi.org/10.1016/j.jacr.2021.08.022

Alnaqbi, N. M., & Fouda, W. (2023). Exploring the role of ChatGPT and social media in enhancing student evaluation of teaching styles in higher education using neutrosophic sets. International Journal of Neutrosophic Science, 20 (4), 181–190. https://doi.org/10.1111/nin.12556

Alqahtani, T., Badreldin, H. A., Alrashed, M., Alshaya, A. I., Alghamdi, S. S., bin Saleh, K., ... & Albekairy, A. M. (2023). The emergent role of artificial intelligence, natural learning processing, and large language models in higher education and research. Research in Social and Administrative Pharmacy. https://doi.org/10.1016/j.sapharm.2023.05.016

Ancillai, C., Sabatini, A., Gatti, M., & Perna, A. (2023). Digital technology and business model innovation: A systematic literature review and future research agenda. Technological Forecasting and Social Change, 188 , 122307. https://doi.org/10.1016/j.techfore.2022.122307

Banić, B., Konecki, M., & Konecki, M. (2023, May). Pair Programming Education Aided by ChatGPT. In 2023 46th MIPRO ICT and Electronics Convention (MIPRO) (pp. 911–915). IEEE.

Busch, F., Adams, L. C., & Bressem, K. K. (2023). Biomedical ethical aspects towards the implementation of artificial intelligence in medical education. Medical Science Educator., 33 , 1007–1012. https://doi.org/10.1007/s40670-023-01815-x

Article   PubMed   PubMed Central   Google Scholar  

Chang, C.-Y., Kuo, S.-Y., & Hwang, G.-H. (2022). Chatbot-facilitated nursing education: Incorporating a knowledge-based Chatbot system into a nursing training program. Educational Technology & Society , 25 (1), 15–27. Retrieved December 19, 2023, from https://www.jstor.org/stable/48647027

Charmaz, K., & Thornberg, R. (2021). The pursuit of quality in grounded theory. Qualitative Research in Psychology, 18 (3), 305–327. https://doi.org/10.1080/14780887.2020.1780357

Choi, E. P. H., Lee, J. J., Ho, M. H., Kwok, J. Y. Y., & Lok, K. Y. W. (2023). Chatting or cheating? The impacts of ChatGPT and other artificial intelligence language models on nurse education. Nurse Education Today, 125 , 105796–105796. https://doi.org/10.1016/j.nedt.2023.105796

Article   PubMed   Google Scholar  

Cooper, G. (2023). Examining science education in chatgpt: An exploratory study of generative artificial intelligence. Journal of Science Education and Technology, 32 (3), 444–452. https://doi.org/10.1007/s10956-023-10039-y

Article   ADS   Google Scholar  

Cross, J., Robinson, R., Devaraju, S., Vaughans, A., Hood, R., Kayalackakom, T., ... & Robinson, R. E. (2023). Transforming medical education: Assessing the integration of ChatGPT into faculty workflows at a Caribbean medical school. Cureus , 15 (7). https://doi.org/10.7759/cureus.41399

Currie, G. M. (2023, May). Academic integrity and artificial intelligence: Is ChatGPT hype, hero or heresy? In Seminars in Nuclear Medicine. WB Saunders. https://doi.org/10.1053/j.semnuclmed.2023.04.008

Das, D., Kumar, N., Longjam, L. A., Sinha, R., Roy, A. D., Mondal, H., & Gupta, P. (2023). Assessing the capability of ChatGPT in answering first-and second-order knowledge questions on microbiology as per competency-based medical education curriculum. Cureus , 15 (3). https://doi.org/10.7759/cureus.36034

Deacon, B., Laufer, M., & Schäfer, L. O. (2023). Infusing educational technologies in the heart of the university-a systematic literature review from an organisational perspective. British Journal of Educational Technology, 54 (2), 441–466. https://doi.org/10.1111/bjet.13277

Deeley, S. J. (2018). Using technology to facilitate effective assessment for learning and feedback in higher education. Assessment & Evaluation in Higher Education, 43 (3), 439–448. https://doi.org/10.1080/02602938.2017.1356906

Deng, X., & Yu, Z. (2023). A meta-analysis and systematic review of the effect of chatbot technology use in sustainable education. Sustainability, 15 (4), 2940. https://doi.org/10.3390/su15042940

Diekemper, R. L., Ireland, B. K., & Merz, L. R. (2015). Development of the documentation and appraisal review tool for systematic reviews. World Journal of Meta-Analysis, 3 (3), 142–150. https://doi.org/10.13105/wjma.v3.i3.142

Engel, A., & Coll, C. (2022). Hybrid teaching and learning environments to promote personalized learning. RIED-Revista Iberoamericana de Educacion a Distancia , 225–242. https://doi.org/10.5944/ried.25.1.31489

Escotet, M. Á. (2023). The optimistic future of Artificial Intelligence in higher education. Prospects, 1–10. https://doi.org/10.1007/s11125-023-09642-z

Esplugas, M. (2023). The use of artificial intelligence (AI) to enhance academic communication, education and research: A balanced approach. Journal of Hand Surgery (European Volume) , 48 (8), 819–822.  https://doi.org/10.1177/17531934231185746

Extance, A. (2023). ChatGPT has entered the classroom: How LLMs could transform education. Nature, 623 , 474–477. https://doi.org/10.1038/d41586-023-03507-3

Article   CAS   PubMed   ADS   Google Scholar  

Foroughi, B., Senali, M. G., Iranmanesh, M., Khanfar, A., Ghobakhloo, M., Annamalai, N., & Naghmeh-Abbaspour, B. (2023). Determinants of Intention to Use ChatGPT for Educational Purposes: Findings from PLS-SEM and fsQCA. International Journal of Human-Computer Interaction , 1–20. https://doi.org/10.1080/10447318.2023.2226495

Gaur, A., & Kumar, M. (2018). A systematic approach to conducting review studies: An assessment of content analysis in 25 years of IB research. Journal of World Business, 53 (2), 280–289. https://doi.org/10.1016/j.jwb.2017.11.003

Ghorbani, M., Bahaghighat, M., Xin, Q., & Özen, F. (2020). ConvLSTMConv network: A deep learning approach for sentiment analysis in cloud computing. Journal of Cloud Computing, 9 (1), 1–12. https://doi.org/10.1186/s13677-020-00162-1

Glaser, B., & Strauss, A. (2017). Discovery of grounded theory: Strategies for qualitative research . Routledge https://doi.org/10.1016/j.jwb.2017.11.003

Gough, D., Oliver, S., & Thomas, J. (Eds.). (2017). An introduction to systematic reviews . Sage https://doi.org/10.5124/jkma.2014.57.1.49

Grant, N., & Metz, C. (2022). A new chat bot is a ‘code red’ for Google's search business, The New York Times. Available at: https://www.nytimes.com/2022/12/21/technology/ai-chatgpt-google-search.html . Accessed 19 Dec 2023

Hadi, M. S., & Junor, R. S. (2022). Speaking to devices: Can we use Google assistant to Foster Students' speaking skills? Journal of Languages and Language Teaching, 10 (4), 570–578. https://doi.org/10.33394/jollt.v10i4.5808

Heng, J. J., Teo, D. B., & Tan, L. F. (2023). The impact of Chat Generative Pre-trained Transformer (ChatGPT) on medical education. Postgraduate Medical Journal , qgad058. https://doi.org/10.1093/postmj/qgad058

Ho, W., & Lee, D. (2023). Enhancing engineering education in the roblox metaverse: Utilizing chatgpt for game development for electrical machine course. International Journal on Advanced Science, Engineering & Information Technology , 13 (3). https://doi.org/10.18517/ijaseit.13.3.18458

Holmes, W., & Kay, J. (2023, June). AI in education. Coming of age? The community voice. In International conference on artificial intelligence in education (pp. 85–90). Springer Nature Switzerland.

Google Scholar  

Hsu, Y. C., & Ching, Y. H. (2023). Generative Artificial Intelligence in Education, Part One: the Dynamic Frontier. TechTrends , 1–5. https://doi.org/10.1007/s11528-023-00863-9

Hwang, G. J., & Chang, C. Y. (2021). A review of opportunities and challenges of chatbots in education. Interactive Learning Environments , 1–14. https://doi.org/10.1080/10494820.2021.1952615

Jalil, S., Rafi, S., LaToza, T. D., Moran, K., & Lam, W. (2023, April). Chatgpt and software testing education: Promises & perils. In 2023 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW) (pp. 4130–4137). IEEE.

Jeon, J., & Lee, S. (2023). Large language models in education: A focus on the complementary relationship between human teachers and ChatGPT. Education and Information Technologies , 1–20. https://doi.org/10.1007/s10639-023-11834-1

Jing, Y., Wang, C., Chen, Y., Wang, H., Yu, T., & Shadiev, R. (2023). Bibliometric mapping techniques in educational technology research: A systematic literature review. Education and Information Technologies , 1–29. https://doi.org/10.1007/s10639-023-12178-6

Johnson, R. B., & Onwuegbuzie, A. J. (2004). Mixed methods research: A research paradigm whose time has come. Educational Researcher, 33 (7), 14–26. https://doi.org/10.3102/0013189X033007014

Karabacak, M., Ozkara, B. B., Margetis, K., Wintermark, M., & Bisdas, S. (2023). The advent of generative language models in medical education. JMIR Medical Education, 9 , e48163. https://doi.org/10.2196/48163

Kasneci, E., Seßler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., … Kasneci, G. (2023). ChatGPT for good? On opportunities and challenges of large language models for education. Learning and Individual Differences, 103 , 102274. https://doi.org/10.1016/j.lindif.2023.102274

Kepuska, V., & Bohouta, G. (2018, January). Next-generation of virtual personal assistants (microsoft cortana, apple siri, amazon alexa and google home). In 2018 IEEE 8th annual computing and communication workshop and conference (CCWC) (pp. 99–103). IEEE.

Kerneža, M. (2023). Fundamental And Basic Cognitive Skills Required For Teachers To Effectively Use Chatbots In Education. In Science And Technology Education: New Developments And Innovations (pp. 99–110). Scientia Socialis, UAB.

Kılıçkaya, F. (2020). Using a chatbot, Replika, to practice writing through conversations in L2 English: A Case study. In New Technological applications for foreign and second language learning and teaching (pp. 221–238). IGI Global. https://doi.org/10.4018/978-1-7998-2591-3.ch011

Killian, C. M., Marttinen, R., Howley, D., Sargent, J., & Jones, E. M. (2023). “Knock, Knock... Who’s There?” ChatGPT and Artificial Intelligence-Powered Large Language Models: Reflections on Potential Impacts Within Health and Physical Education Teacher Education. Journal of Teaching in Physical Education , 1 (aop), 1–5. https://doi.org/10.1123/jtpe.2023-0058

Kohnke, L. (2022). A pedagogical Chatbot: A supplemental language learning Tool. RELC Journal , 00336882211067054. https://doi.org/10.1177/00336882211067054

Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., ... & Tseng, V. (2023). Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLoS Digital Health, 2 (2), e0000198. https://doi.org/10.1371/journal.pdig.0000198

Lee, D., & Yeo, S. (2022). Developing an AI-based chatbot for practicing responsive teaching in mathematics. Computers & Education, 191 , 104646. https://doi.org/10.1016/j.compedu.2022.104646

Lee, L. W., Dabirian, A., McCarthy, I. P., & Kietzmann, J. (2020). Making sense of text: Artificial intelligence-enabled content analysis. European Journal of Marketing, 54 (3), 615–644. https://doi.org/10.1108/EJM-02-2019-0219

Li, L., Ma, Z., Fan, L., Lee, S., Yu, H., & Hemphill, L. (2023). ChatGPT in education: A discourse analysis of worries and concerns on social media. arXiv preprint arXiv :2305.02201. https://doi.org/10.48550/arXiv.2305.02201

Lim, W. M., Gunasekara, A., Pallant, J. L., Pallant, J. I., & Pechenkina, E. (2023). Generative AI and the future of education: Ragnarök or reformation? A paradoxical perspective from management educators. The International Journal of Management Education, 21 (2), 100790. https://doi.org/10.1016/j.ijme.2023.100790

Lin, T. J., & Lan, Y. J. (2015). Language learning in virtual reality environments: Past, present, and future. Journal of Educational Technology & Society, 18 (4), 486–497. Retrieved December 19, 2023, from http://www.jstor.org/stable/jeductechsoci.18.4.486

Lodge, J. M., Thompson, K., & Corrin, L. (2023). Mapping out a research agenda for generative artificial intelligence in tertiary education. Australasian Journal of Educational Technology, 39 (1), 1–8. https://doi.org/10.14742/ajet.8695

Luo, H., Li, G., Feng, Q., Yang, Y., & Zuo, M. (2021). Virtual reality in K-12 and higher education: A systematic review of the literature from 2000 to 2019. Journal of Computer Assisted Learning, 37 (3), 887–901. https://doi.org/10.1111/jcal.12538

Mariani, M. M., Hashemi, N., & Wirtz, J. (2023). Artificial intelligence empowered conversational agents: A systematic literature review and research agenda. Journal of Business Research, 161 , 113838. https://doi.org/10.1016/j.jbusres.2023.113838

Mohamed, A. M. (2023). Exploring the potential of an AI-based Chatbot (ChatGPT) in enhancing English as a Foreign Language (EFL) teaching: perceptions of EFL Faculty Members. Education and Information Technologies, 1–23. https://doi.org/10.1007/s10639-023-11917-z

Mohammad, B., Supti, T., Alzubaidi, M., Shah, H., Alam, T., Shah, Z., & Househ, M. (2023). The pros and cons of using ChatGPT in medical education: A scoping review. Student Health Technology Information, 305 , 644–647. https://doi.org/10.3233/SHTI230580

Moher, D., Liberati, A., Tetzlaff, J., Altman, D. G., & PRISMA Group. (2009). Preferred reporting items for systematic reviews and meta-analyses: The PRISMA statement. Annals of Internal Medicine, 151 , 264–269. https://doi.org/10.7326/0003-4819-151-4-200908180-00135

Mokmin, N. A. M., & Ibrahim, N. A. (2021). The evaluation of chatbot as a tool for health literacy education among undergraduate students. Education and Information Technologies, 26 (5), 6033–6049. https://doi.org/10.1007/s10639-021-10542-y

Patel, N., Nagpal, P., Shah, T., Sharma, A., Malvi, S., & Lomas, D. (2023). Improving mathematics assessment readability: Do large language models help? Journal of Computer Assisted Learning, 39 (3), 804–822. https://doi.org/10.1111/jcal.12776

Paul, J., Lim, W. M., O’Cass, A., Hao, A. W., & Bresciani, S. (2021). Scientific procedures and rationales for systematic literature reviews (SPAR-4-SLR). International Journal of Consumer Studies, 45 (4), O1–O16. https://doi.org/10.1111/ijcs.12695

Pentina, I., Xie, T., Hancock, T., & Bailey, A. (2023). Consumer–machine relationships in the age of artificial intelligence: Systematic literature review and research directions. Psychology & Marketing, 40 (8), 1593–1614. https://doi.org/10.1002/mar.21853

Pereira, R., Reis, A., Barroso, J., Sousa, J., & Pinto, T. (2022). Virtual assistants applications in education. In International conference on technology and innovation in learning, teaching and education (pp. 468–480). Springer Nature Switzerland.

Pinto, A. S., Abreu, A., Costa, E., & Paiva, J. (2023). How Machine Learning (ML) is transforming higher education: A systematic literature review. Journal of Information Systems Engineering and Management, 8 (2). https://doi.org/10.55267/iadt.07.13227

Prikshat, V., Islam, M., Patel, P., Malik, A., Budhwar, P., & Gupta, S. (2023). AI-augmented HRM: Literature review and a proposed multilevel framework for future research. Technological Forecasting and Social Change, 193 , 122645. https://doi.org/10.1016/j.techfore.2023.122645

Radianti, J., Majchrzak, T. A., Fromm, J., & Wohlgenannt, I. (2020). A systematic review of immersive virtual reality applications for higher education: Design elements, lessons learned, and research agenda. Computers & Education, 147 , 103778. https://doi.org/10.1016/j.compedu.2019.103778

Rahimzadeh, V., Kostick-Quenet, K., Blumenthal Barby, J., & McGuire, A. L. (2023). Ethics education for healthcare professionals in the era of chatGPT and other large language models: Do we still need it?. The American Journal of Bioethics , 1–11. https://doi.org/10.1080/15265161.2023.2233358

Rahman, M. M., & Watanobe, Y. (2023). ChatGPT for education and research: Opportunities, threats, and strategies. Applied Sciences, 13 (9), 5783. https://doi.org/10.3390/app13095783

Article   CAS   Google Scholar  

Rasul, T., Nair, S., Kalendra, D., Robin, M., de Oliveira Santini, F., Ladeira, W. J., ... & Heathcote, L. (2023). The role of ChatGPT in higher education: Benefits, challenges, and future research directions. Journal of Applied Learning and Teaching, 6 (1). https://doi.org/10.37074/jalt.2023.6.1

Sallam, M. (2023a). ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. In Healthcare (Vol. 11, No. 6, p. 887). MDPI. https://doi.org/10.3390/healthcare11060887

Sallam, M. (2023b). ChatGPT utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns. Healthcare, 11 (6), 887. https://doi.org/10.3390/healthcare11060887

Sánchez-Ruiz, L. M., Moll-López, S., Nuñez-Pérez, A., Moraño-Fernández, J. A., & Vega-Fleitas, E. (2023). ChatGPT challenges blended learning methodologies in engineering education: A case study in mathematics. Applied Sciences, 13 (10), 6039. https://doi.org/10.3390/app13106039

Sandu, N., & Gide, E. (2019). Adoption of AI-Chatbots to enhance student learning experience in higher education in India. In 2019 18th International Conference on Information Technology Based Higher Education and Training (ITHET) (pp. 1–5). IEEE.

Schmulian, A., & Coetzee, S. A. (2019). Students’ experience of team assessment with immediate feedback in a large accounting class. Assessment & Evaluation in Higher Education, 44 (4), 516–532. https://doi.org/10.1080/02602938.2018.1522295

Seetharaman, R. (2023). Revolutionizing medical education: Can ChatGPT boost subjective learning and expression? Journal of Medical Systems, 47 (1), 1–4. https://doi.org/10.1007/s10916-023-01957-w

Sharma, M., & Sharma, S. (2023). A holistic approach to remote patient monitoring, fueled by ChatGPT and Metaverse technology: The future of nursing education. Nurse Education Today, 131 , 105972. https://doi.org/10.1016/j.nedt.2023.105972

Shlonsky, A., Noonan, E., Littell, J. H., & Montgomery, P. (2011). The role of systematic reviews and the Campbell collaboration in the realization of evidence-informed practice. Clinical Social Work Journal, 39 , 362–368. https://doi.org/10.1007/s10615-010-0307-0

Shoja, M. M., Van de Ridder, J. M., & Rajput, V. (2023). The emerging role of generative artificial intelligence in medical education, research, and practice. Cureus, 15 (6), e40883. https://doi.org/10.7759/cureus.40883

Siegle, D. (2023). A role for ChatGPT and AI in gifted education. Gifted Child Today, 46 (3), 211–219. https://doi.org/10.1177/10762175231168443

Smith, A., Hachen, S., Schleifer, R., Bhugra, D., Buadze, A., & Liebrenz, M. (2023). Old dog, new tricks? Exploring the potential functionalities of ChatGPT in supporting educational methods in social psychiatry. International Journal of Social Psychiatry . https://doi.org/10.1177/0020764023117845

Strzelecki, A. (2023). To use or not to use ChatGPT in higher education? A study of students’ acceptance and use of technology. Interactive Learning Environments , 1–14. https://doi.org/10.1080/10494820.2023.2209881

Tam, W., Huynh, T., Tang, A., Luong, S., Khatri, Y., & Zhou, W. (2023). Nursing education in the age of artificial intelligence powered Chatbots (AI-Chatbots): Are we ready yet? Nurse Education Today, 129 , 105917. https://doi.org/10.1016/j.nedt.2023.105917

Teel, Z. A., Wang, T., & Lund, B. (2023). ChatGPT conundrums: Probing plagiarism and parroting problems in higher education practices. College & Research Libraries News, 84 (6), 205. https://doi.org/10.5860/crln.84.6.205

Tlili, A., Shehata, B., Adarkwah, M. A., Bozkurt, A., Hickey, D. T., Huang, R., & Agyemang, B. (2023). What if the devil is my guardian angel: ChatGPT as a case study of using chatbots in education. Smart Learning Environments, 10 (1), 15. https://doi.org/10.1186/s40561-023-00237-x

Tsang, R. (2023). Practical applications of ChatGPT in undergraduate medical education. Journal of Medical Education and Curricular Development , 10 . https://doi.org/10.1177/23821205231178449

Yan, D. (2023). Impact of ChatGPT on learners in a L2 writing practicum: An exploratory investigation. Education and Information Technologies, 1–25. https://doi.org/10.1007/s10639-023-11742-4

Zhang, R., Zou, D., & Cheng, G. (2023a). A review of chatbot-assisted learning: pedagogical approaches, implementations, factors leading to effectiveness, theories, and future directions. Interactive Learning Environments , 1–29. https://doi.org/10.1080/10494820.2023.2202704

Zhang, S., Shan, C., Lee, J. S. Y., Che, S., & Kim, J. H. (2023b). Effect of chatbot-assisted language learning: A meta-analysis. Education and Information Technologies , 1–21. https://doi.org/10.1007/s10639-023-11805-6

Zhu, C., Sun, M., Luo, J., Li, T., & Wang, M. (2023). How to harness the potential of ChatGPT in education? Knowledge Management & E-Learning, 15 (2), 133. https://doi.org/10.34105/j.kmel.2023.15.008

Download references

Author information

Authors and affiliations.

College of Educational Science and Technology, Zhejiang University of Technology, Hangzhou, China

Xiaojiao Chen

College of Foreign Languages, Zhejiang University of Technology, Hangzhou, China

Department of Education Information Technology, Faculty of Education, East China Normal University, Shanghai, China

Chengliang Wang

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Chengliang Wang .

Ethics declarations

Conflict of interest.

During the research, the authors indicate that no commercial or financial ties that may be regarded a possible conflict of interest existed.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Chen, X., Hu, Z. & Wang, C. Empowering education development through AIGC: A systematic literature review. Educ Inf Technol (2024). https://doi.org/10.1007/s10639-024-12549-7

Download citation

Received : 19 October 2023

Accepted : 05 February 2024

Published : 29 February 2024

DOI : https://doi.org/10.1007/s10639-024-12549-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Artificial intelligence generated content
• Artificial intelligence
• Systematic literature review
• Educational technology
• Find a journal
• Publish with us
• Track your research

Oh no, you're thinking, yet another cookie pop-up. Well, sorry, it's the law. We measure how many people read us, and ensure you see relevant ads, by storing cookies on your device. If you're cool with that, hit “Accept all Cookies”. For more info and to customize your settings, hit “Customize Settings”.

Review and manage your consent

Here's an overview of our use of cookies, similar technologies and how to manage them. You can also change your choices at any time, by hitting the “Your Consent Options” link on the site's footer.

Manage Cookie Preferences

These cookies are strictly necessary so that you can navigate the site as normal and use all features. Without these cookies we cannot provide you with the service that you expect.

These cookies are used to make advertising messages more relevant to you. They perform functions like preventing the same ad from continuously reappearing, ensuring that ads are properly displayed for advertisers, and in some cases selecting advertisements that are based on your interests.

These cookies collect information in aggregate form to help us understand how our websites are being used. They allow us to count visits and traffic sources so that we can measure and improve the performance of our sites. If people say no to these cookies, we do not know how many people have visited and we cannot monitor performance.

Special Features

Vendor voice.

AI researchers have started reviewing their peers using AI assistance

Chatgpt deems your work to be commendable, innovative, and comprehensive.

Academics focused on artificial intelligence have taken to using generative AI to help them review the machine learning work of peers.

A group of researchers from Stanford University, NEC Labs America, and UC Santa Barbara recently analyzed the peer reviews of papers submitted to leading AI conferences, including ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023.

The authors – Weixin Liang, Zachary Izzo, Yaohui Zhang, Haley Lepp, Hancheng Cao, Xuandong Zhao, Lingjiao Chen, Haotian Ye, Sheng Liu, Zhi Huang, Daniel A McFarland, and James Y Zou – reported their findings in a paper titled "Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews."

They undertook the study based on the public interest in, and discussion of, large language models that dominated technical discourse last year.

The authors found a small but consistent increase in apparent LLM usage for reviews submitted three days or less before the deadline

The difficulty of distinguishing between human- and machine-written text and the reported rise in AI news websites led the authors to conclude that there's an urgent need to develop ways to evaluate real-world data sets that contain some indeterminate amount of AI-authored content.

Sometimes AI authorship stands out – as in a paper from Radiology Case Reports entitled "Successful management of an Iatrogenic portal vein and hepatic artery injury in a 4-month-old female patient: A case report and literature review."

This jumbled passage is a bit of a giveaway: "In summary, the management of bilateral iatrogenic I'm very sorry, but I don't have access to real-time information or patient-specific data, as I am an AI language model."

But the distinction isn't always obvious, and past attempts to develop an automated way to sort human-written text from robo-prose have not gone well. OpenAI, for example introduced an AI Text Classifier for that purpose in January 2023, only to shutter it six months later " due to its low rate of accuracy ."

Nonetheless, Liang et al contend that focusing on the use of adjectives in a text – rather than trying to assess entire documents, paragraphs, or sentences – leads to more reliable results.

The authors took two sets of data, or corpora – one written by humans and the other one written by machines. And they used these two bodies of text to evaluate the evaluations – the peer reviews of conference AI papers – for the frequency of specific adjectives.

• Grok-1 chatbot code released – open source or open Pandora's box?
• Top LLMs struggle to make accurate legal arguments
• In the rush to build AI apps, please, please don't leave security behind
• Google launches Gemini AI systems, claims it's beating OpenAI and others - mostly

"[A]ll of our calculations depend only on the adjectives contained in each document," they explained. "We found this vocabulary choice to exhibit greater stability than using other parts of speech such as adverbs, verbs, nouns, or all possible tokens."

It turns out LLMs tend to employ adjectives like "commendable," "innovative," and "comprehensive" more frequently than human authors. And such statistical differences in word usage have allowed the boffins to identify reviews of papers where LLM assistance is deemed likely.

Word cloud of top 100 adjectives in LLM feedback, with font size indicating frequency (click to enlarge)

"Our results suggest that between 6.5 percent and 16.9 percent of text submitted as peer reviews to these conferences could have been substantially modified by LLMs, i.e. beyond spell-checking or minor writing updates," the authors argued, noting that reviews of work in the scientific journal Nature do not exhibit signs of mechanized assistance.

Several factors appear to be correlated with greater LLM usage. One is an approaching deadline: The authors found a small but consistent increase in apparent LLM usage for reviews submitted three days or less before the deadline.

The researchers emphasized that their intention was not to pass judgment on the use of AI writing assistance, nor to claim that any of the papers they evaluated were written completely by an AI model. But they argued the scientific community needs to be more transparent about the use of LLMs.

And they contended that such practices potentially deprive those whose work is being reviewed of diverse feedback from experts. What's more, AI feedback risks a homogenization effect that skews toward AI model biases and away from meaningful insight. ®

• Large Language Model

Narrower topics

• AdBlock Plus
• Application Delivery Controller
• Graphics Interchange Format
• Legacy Technology
• LibreOffice
• Machine Learning
• Microsoft 365
• Microsoft Office
• Microsoft Teams
• Mobile Device Management
• Neural Networks
• Programming Language
• Retro computing
• Search Engine
• Software bug
• Software License
• Tensor Processing Unit
• Text Editor
• User interface
• Visual Studio
• Visual Studio Code
• WebAssembly
• Web Browser

Broader topics

• Self-driving Car

Send us news

Other stories you might like

You got legal trouble better call saulm-7b, nvidia: why write code when you can string together a couple chat bots, ai models show racial bias based on written dialect, researchers find, a different view from the edge.

Apple iPhone AI to be powered by Baidu in China, maybe

Ai mishaps are surging – and now they're being tracked like software bugs, ai and wearables are scaring the wellbeing out of workers, your pc can probably run inferencing just fine – so it's already an ai pc, cruise's valuation halved after its driverless car hit and dragged a woman, samsung preps inferencing accelerator to take on nvidia, scores huge sale, amd hires former oak ridge chief to punt ai to governments, dell adds nvidia's next gpus to its portfolio of ai platforms.

• Advertise with us

Our Websites

• The Next Platform
• Blocks and Files

Your Privacy

• Cookies Policy
• Your Consent Options
• Privacy Policy
• Ts & Cs

Copyright. All rights reserved © 1998–2024

Do hours worth of reading in minutes

Try asking or searching for:

Popular papers to read

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Attention is All you Need

mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Deformable DETR: Deformable Transformers for End-to-End Object Detection

How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models

Machine Learning

Support-Vector Networks

Distributed Optimization and Statistical Learning Via the Alternating Direction Method of Multipliers

Learning Deep Architectures for AI

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

An Introduction to Support Vector Machines

Model-agnostic meta-learning for fast adaptation of deep networks

Semi-supervised learning using Gaussian fields and harmonic functions

Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples

Support vector machine learning for interdependent and structured output spaces

A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data

Natural Language

Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference

Learning Transferable Visual Models From Natural Language Supervision

Unified Pre-training for Program Understanding and Generation

Semantic memory: A review of methods, models, and current challenges

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios.

Foundations of Statistical Natural Language Processing

A framework for representing knowledge

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognitio

Semantic similarity in a taxonomy: an information-based measure and its application to problems of ambiguity in natural language

Cheap and Fast -- But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks

Top papers of 2023

Top papers of 2022, trending questions, what is the current understanding of chikv infection in pediatric populations, is duochrome test accurate for hyperopia, what are the key principles of quality management, are lateral heel wedges effective against knee osteoarthritis, what are the diagnostic criteria for alzheimer's disease, what research statistics can be used to analyze inter-rater agreement, how do economic conditions, such as inflation and exchange rates, affect labor costs across countries, what is the current state of research on empirical causal inference in fiscal monetization, how does nutrition and diet affects in academic performance of senior highschool, what is the english proficiency of filipino, what are the most common interview questions used to understand online shopping experiences of customers, what is quantum dot, what are the long-term effects of fiscal monetization on inflation rates, how does pleasing items help students to be academically motivated, how does receptive and productive knowledge of english tenses help all language skills, how does job networking help college students studying to be mental health and addiction professionals, what research design or method to analyze inter-rater agreement, what are the challenges of student engagement in higher education, how to evaluate chatbot, what psychological needs do memorials within psychology serve, for both the individuals involved and the broader field, what tools are there to categorise chronic foot wounds, how does job networking help college students studying to be healthcare workers, what are green practices in hotels, what are current macroeconomic conditions that affect ecommerce, is respect for authority must be learn since childhood, in what ways do memorials contribute to the field of psychology's understanding and management of grief and loss, what is the relationship between the amount of time spent playing mobile games and academic performance in students, what is active space in architecture, why should student engagement in higher education be studied, is fluticasone propionate effective for eye symptoms, what is the ideal singapore citizen, smart agriculture and irrigation management, how to analyse cut and paste video authentication, recent research gap on hiv screening and mental health, what other researchers say about cash depositing machine in terms of efficiency in recording money and counting money, can interactive journaling be used as a tool for personal growth and self-improvement, and if so, how, can resilience be used as a proactive approach to mitigate potential security risks, how does age affects cognitive interaction with ai in education, what are the news, how do modern methods of construction (mmc) impact fire safety regulations and preventive measures in traditional building approaches, what are the news on filipino reading comprehension, what is the relationship between motivation and engagement in english language learning, what is the ratio of protein yield between nucleus and cytoplasm, islamic practice critical ill patients, is there any recovery oriented training for nurse managers, which gasdermin protein is well studied, what is the effect of hydrous and anhydrous form on the drug solubility, what factors influence the intention to adopt fintech among individuals with different levels of education, what are the specific challenges faced by student journalists in the digital age, how does social media affects economics, what research is there into homophily and face matching, does the shareholding nature affect the audit fee, article about potential of the inovative product, how does cash flow management affect the economic development of underdeveloped communities, when cs3cu2i5 suffer oxidation, does the cscu2i3 phase is formed, what neural networks could i use to denoise an audio, what is 2d shape morphing, survey questionnaire for reading skills in english, eu monitor and prevent money laundering through cryptocurrency/digital assets, what are the specific esg indicators used to measure water sustainability in ports, is there a self-reported scale that measures sustained attention at work, is there a self-reported scale that measures sustained attention, what is geometric morphing of planar shapes, is there an e. coli strain that secretes lactase, how effective are polycentric policies in promoting sustainable development in metropolitan regions, is geoeconomics a new issue in the philippines, what is positive mental health, what are the potential applications of copper-bismuth-vanadium catalysts in the chemical industry, what are the human factors caused desertification in china, how mining sector contribute australian ghg emission prodcution , what is the difference between integrated satisfaction and overall satisfaction, what are the types of sports injuries in soccer, article about potential of the inovative product that is muruku, what is the relationship between students' learning styles and engagement in english language learning, what are the specific challenges that seniors face in transitioning to sustainable aviation practices, how does lecture based learning approach affect the academic performance of the students, is ph higher in the middle of the day, s1pr modulator가 infection의 위험이 높아, is there any guideline for a goods practice of lease agreements for residential and commercial properties , is there any paper that gel electrolyte with nanocellulose dispersion, how does technology help teachers teach., what is the relationship between sensitivity to pain and depression, what factors contribute to the measurement of integrated satisfaction, the benefits of st john wort, what is the relationship between learner preferences for learning english and learner engagement, what are some innovative financial inclusion strategies that have been successful in promoting economic growth in underdeveloped communities, what is multiple universe theory, how do microplastics interact with marine ecosystems and what impact does this have on biodiversity, where is predictive maintenance used in shipping or shipbuilding, what is active open space in urban planning, which beta-lactam antibiotics are used against staphylococcus aureus, why does the lecture based learning approach leads to poor academic performance, what are the reasons for the berne convention on copyright, what's the scientific opportunity for time-resolved spectroscopy, how do job demands impact the exhaustion levels of partners in a romantic relationship, what is the impact of hajj pilgrimage on the spiritual and psychological well-being of muslim individuals, what is the impact of bipolar disorder on preetha shenoy's life as depicted in the phrase, what is the theory of negativity bias, what are the challenges for thai msmes to digitalize supplu chain, what is the current state of research on performance analysis and verification of elastic circuits under process variations, 🔬 researchers worldwide are simplifying papers.

Millions of researchers are already using SciSpace on research papers. Join them and start using your AI research assistant wherever you're reading online.

Mushtaq Bilal, PhD

Researcher @ Syddansk Universitet

SciSpace is an incredible (AI-powered) tool to help you understand research papers better. It can explain and elaborate most academic texts in simple words.

Olesia Nikulina

PhD Candidate

Academic research gets easier day by day. All thanks to AI tools like @scispace Copilot, Copilot can instantly answer your questions and simply explain scientific concepts as you read

Richard Gao

Co-founder evoke-app.com

This is perfect for a layman to scientific information like me. Especially with so much misinformation floating around nowadays, this is great for understanding studies or research others may have misrepresented on purpose or by accident.

Product Hunt

I absolutely adore this product. It's been years since I was in a lab but, I plugged in a study I did way back when and this gets everything right. Equations, hypotheses, and methodologies will be game changers for graduate studies (the current education system severely limits comprehension while encouraging interconnectivity between streams). But, early learners would be able to discover so many papers through this as well. In short, love it

Livia Burbulea

I'm gonna recommend SciSpace to all of my friends and family that are still studying. And I'll definitely love to give it a try for myself, cause you know, education should never stop when you finish your studies. 😀

Sara Botticelli

Product Hunt User.

Wonderful idea! I know this will be used and appreciated by a lot of students, researchers, and lovers of knowledge. Great job, team @saikiranchandha and @shanukumr!

Divyansh Verma

SVNIT'25 Chemical Engineering

SciSpace, is a website where you can easily conduct research. Its most notable feature, in my opinion, is the presence of a #ai-powered copilot which can #simplify and explain any text you highlight in the paper you're reading. #citations and related papers are easily accessible with each paper.

Researcher @ VIU

It´s not only the saved time. Reading scientific literature, specially if you are not an expert in the field is a very attention-intensive process. It´s not a task you can maintain for long periods of time. Having them not just smartly summarised but being able to get meaningful answers is a game-changer for a science journalist

Kalyani Korla, PhD

Product Manager • Healthcare

Upload your pdf and highlight the sections you want to understand. It simplifies those complicated sections of the article in a jiffy. It is not rocket science, but it is always welcome if someone explains the big terms in simpler words.

In the media

Research with Generative AI

Resources for scholars and researchers

Generative AI (GenAI) technologies offer new opportunities to advance research and scholarship. This resource page aims to provide Harvard researchers and scholars with basic guidance, information on available resources, and contacts. The content will be regularly updated as these technologies continue to evolve. Your feedback is welcome.

Leading the way

Harvard’s researchers are making strides not only on generative AI, but the larger world of artificial intelligence and its applications. Learn more about key efforts.

The Kempner Institute

The Kempner Institute is dedicated to revealing the foundations of intelligence in both natural and artificial contexts, and to leveraging these findings to develop groundbreaking technologies.

Harvard Data Science Initiative

The Harvard Data Science Initiative is dedicated to understanding the many dimensions of data science and propelling it forward.

More AI @ Harvard

Generative AI is only part of the fascinating world of artificial intelligence. Explore Harvard’s groundbreaking and cross-disciplinary academic work in AI.

funding opportunity

William F. Milton Fund: Generative AI Track

The William F. Milton Fund, established in 1924, is one of the oldest bequests made to Harvard University. This year, the Milton Fund has opened a second track of applications designed to encourage the exploration and application of generative AI in research settings.

Learn more and apply

Frequently asked questions

Can i use generative ai to write and/or develop research papers.

Academic publishers have a range of policies on the use of AI in research papers. In some cases, publishers may prohibit the use of AI for certain aspects of paper development. You should review the specific policies of the target publisher to determine what is permitted.

Here is a sampling of policies available online:

• JAMA and the JAMA Network
• Springer Nature

How should AI-generated content be cited in research papers?

Guidance will likely develop as AI systems evolve, but some leading style guides have offered recommendations:

• The Chicago Manual of Style
• MLA Style Guide

Should I disclose the use of generative AI in a research paper?

Yes. Most academic publishers require researchers using AI tools to document this use in the methods or acknowledgements sections of their papers. You should review the specific guidelines of the target publisher to determine what is required.

Can I use AI in writing grant applications?

You should review the specific policies of potential funders to determine if the use of AI is permitted. For its part, the National Institutes of Health (NIH) advises caution : “If you use an AI tool to help write your application, you also do so at your own risk,” as these tools may inadvertently introduce issues associated with research misconduct, such as plagiarism or fabrication.

Can I use AI in the peer review process?

Many funders have not yet published policies on the use of AI in the peer review process. However, the National Institutes of Health (NIH) has prohibited such use “for analyzing and formulating peer review critiques for grant applications and R&D contract proposals.” You should carefully review the specific policies of funders to determine their stance on the use of AI

Are there AI safety concerns or potential risks I should be aware of?

Yes. Some of the primary safety issues and risks include the following:

• Bias and discrimination: The potential for AI systems to exhibit unfair or discriminatory behavior.
• Misinformation, impersonation, and manipulation: The risk of AI systems disseminating false or misleading information, or being used to deceive or manipulate individuals.
• Research and IP compliance: The necessity for AI systems to adhere to legal and ethical guidelines when utilizing proprietary information or conducting research.
• Security vulnerabilities: The susceptibility of AI systems to hacking or unauthorized access.
• Unpredictability: The difficulty in predicting the behavior or outcomes of AI systems.
• Overreliance: The risk of relying excessively on AI systems without considering their limitations or potential errors.

See Initial guidelines for the use of Generative AI tools at Harvard for more information.

• Initial guidelines for the use of Generative AI tools at Harvard

Generative AI tools

• Explore Tools Available to the Harvard Community
• Request API Access
• Request a Vendor Risk Assessment
• Questions? Contact HUIT

Copyright and intellectual property

• Copyright and Fair Use: A Guide for the Harvard Community
• Copyright Advisory Program
• Intellectual Property Policy
• Protecting Intellectual Property

Data security and privacy

• Harvard Information Security and Data Privacy
• Data Security Levels – Research Data Examples
• Privacy Policies and Guidelines

Research support

• University Research Computing and Data (RCD) Services
• Research Administration and Compliance
• Research Computing
• Research Data and Scholarship
• Faculty engaged in AI research
• Centers and initiatives engaged in AI research
• Degree and other education programs in AI