literature review search 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

Ai journalist, text style transfer, one-page report writer.

A free, AI-powered research tool for scientific literature

• Fiona Doyle
• Metaphysics

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.

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..

AI Tools To Automate Your Literature Review: Which To Use?

Researching and writing outa literature review can be a daunting task, but AI-powered tools like Semantic Scholar, Research Rabbit, and Scite are revolutionising this process.

These tools, leveraging artificial intelligence, automate the arduous task of sifting through mountains of academic papers, extracting key information, and summarizing relevant research.

In this article, lets explore how AI research assistants and advanced search engines streamline the literature review process, making it faster, more efficient, and thorough for conducting scientific research. Discover the best AI tools to transform your literature review work. 

Why Use AI Tools To Write Literature Review?

The vast sea of academic papers can be daunting. This is where AI tools like ChatGPT, Semantic Scholar, and Research Rabbit become indispensable.

AI tools for literature review are adept at sifting through millions of papers across various databases like PubMed and Google Scholar. They use AI algorithms and natural language processing (NLP) to identify relevant research articles, providing a summary of key information.

Some AI-powered research assistant such as Scite, uses AI to scan through research data, offering insights into the supporting or contrasting evidence within peer-reviewed papers. This can be a valuable tool for finding specific details in a systematic literature review.

These tools also streamline the literature search by automating the process of citation and reference management. Tools like Connected Papers and Research Rabbit are adept at evaluating and summarizing relevant academic papers, saving you time and effort.

They can extract key information from PDF documents and research articles, making it fast and easy to organize your findings.

AI-powered tools for literature review also help in creating a thorough literature search, essential for:

• Systematic literature reviews
• Meta-analyses, and
• Identifying research gap.

They can elicit information from a variety of sources, providing a comprehensive view of your research question. This approach ensures that your literature review is not only rich in content but also diverse in perspectives.

Best AI Tools To Write Literature Review

If you are looking at exploring AI tools to help you write literature review, consider these instead. They are revolutionizing the way literature reviews are conducted:

Connected Papers

As the name suggests, Connected Papers focuses on showing how various academic papers are interconnected. This generative AI tool helps you visualize the research landscape around your topic, making it easier to:

• Identify key papers,
• Identify potential gaps in your literature review, and
• Understand emerging trends in scientific research.

While not a traditional literature review tool, ChatGPT is revolutionising academic research by offering prompt-based assistance.

This chatbot-like AI tool can help automate parts of the literature review process, such as generating research questions or providing quick summaries of complex topics.

ChatGPT’s AI-driven insights can be a valuable starting point for deeper exploration into specific research areas. The key is to provide it with the right input, and then to give the right prompts.

Research Rabbit

This tool uses AI to scan a variety of sources, including peer-reviewed research data. It’s particularly useful for conducting systematic literature reviews, as it can evaluate and summarize relevant academic papers, highlighting supporting or contrasting evidence.

Its key features include mapping out connections between research papers, identifying key papers in a research area, and helping to understand how various research topics are interconnected.

Research Rabbit also excels in reference management, a vital component of academic writing.

Scite is an innovative tool that uses AI technologies to provide a new layer of insight into scientific literature.

It evaluates the credibility of research by analyzing citation contexts, helping you to identify the most impactful and relevant papers for your research question.

Scite’s most distinctive feature is its Smart Citations. Unlike traditional citations that merely count how often a paper is cited, Smart Citations provide context by showing how a paper has been cited. This means that for each citation, Scite shows you the other relevant papers that:

• Contrasts, or
• Mentioning evidence for the claims made in the original paper. 

As a result, Scite is invaluable for conducting thorough literature reviews, especially for systematic reviews and meta-analyses.

Semantic Scholar

This AI-powered research assistant stands out in its ability to sift through vast databases like PubMed and Google Scholar.

It uses advanced natural language processing (NLP) and AI algorithms to extract key information from millions of academic papers, offering concise summaries and identifying relevant research articles.

What sets Semantic Scholar apart is its AI algorithms. It analyses millions of academic publications, extracting key information such as:

• Figures, 
• Tables, as well as 
• Contextual relevance of each paper.

This enables the tool to provide highly relevant search results, summaries, and insights that are tailored to your specific interests and research needs.

What To Watch Out For When Writing Literature Review With AI Tools?

When you’re writing a literature review with AI tools, you’re stepping into a world where technology meets academic rigor. To ensure they balance each other out, by watching over these details as you use AI when researching:

Bias  

AI algorithms, including those used in literature search tools, can inherit biases from their training data.

This might skew the search results towards more popular or frequently cited papers, potentially overlooking lesser-known yet significant research.

Ensure you’re accessing a variety of sources to maintain a balanced perspective. When possible, always look into newer papers on your research area, as these may not have been discovered by your AI tool yet.

Citation Accuracy

While tools like Scite provide advanced citation analysis, the accuracy of AI in identifying and interpreting citations is not infallible.

Always verify the citations and references manually, especially when dealing with complex literature or less digitised sources.

You can also use multiple AI tools to check for citation accuracy. For example, rather than simply relying on Scite, you can also use other reference management softwares like: 

• Refworks, or

Contextual Understanding

AI tools, efficient as they are, might not fully grasp the nuanced context of your research question.

Tools like ChatGPT and Semantic Scholar provide summaries and identify relevant papers using natural language processing (NLP), but they may not always align perfectly with your specific research focus.

Always double-check that the AI’s interpretation matches your intended research angle. This means actually spending time to read articles within the research area, and become familiar with it. 

Depth of Analysis

AI tools can automate the initial stages of your literature review by quickly sifting through databases like PubMed and Google Scholar to find relevant papers.

However, they might not evaluate the depth and subtlety of arguments in academic writing as thoroughly as a human researcher would.

It’s crucial to supplement AI findings with your own detailed analysis. This means you should not rely on AI completely, but to actually roll up your sleeves and work on the analysis yourself as well.

Over-reliance on AI

There’s a temptation to overly rely on AI for streamlining every aspect of the literature review process.

Remember, AI is a tool to assist, not replace, your critical thinking and scholarly diligence.

Use AI to enhance your workflow but maintain an active role in evaluating and synthesising research data. See AI as a tool, not your replacement. You need to be there to pilot the AI tool, to ensure it is doing its job properly.

AI Tools For Literature Review: Keep Up With Times

Leveraging AI tools for your literature review is a game-changer. Tools like Semantic Scholar, Research Rabbit, and Scite, powered by advanced AI algorithms, not only automate the search for relevant papers but also provide critical summaries and evaluations.

They enhance the literature review process in academic research, making it more efficient and comprehensive.

As AI continues to evolve, these tools become indispensable for researchers, helping to streamline workflows, organize findings, and extract key insights from a vast array of scientific literature with unparalleled ease and speed.

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

• Resources Home 🏠
• Try SciSpace Copilot
• Search research papers
• Add Copilot Extension
• Try AI Detector
• Try Paraphraser
• Try Citation Generator
• April Papers
• June Papers
• July Papers

Introducing SciSpace's all-new AI-powered literature review workspace

Scientists increasingly rely on AI and automation's power to uncover groundbreaking scientific discoveries. And we have a new addition to this toolbox — our all-new AI-powered literature review tool.

Now simply enter a keyword or query, and the AI sorts through thousands of papers in seconds picks out the key themes and trends, extracts relevant insights, and presents everything in an easy-to-understand format. It should help researchers build a solid theoretical framework for their work more efficiently than ever before.

Researchers worldwide have been using our AI assistant, Copilot , to read and understand scientific papers better. Now with the addition of the SciSpace Literature Review, researchers can focus more on experimentation and interpretation and less on manual literature review.

With millions of papers being published each year, it can be challenging to extract meaningful insights related to research. That's why we created SciSpace Literature Review , your mission control for literature review.

Getting started with SciSpace Literature Review

Using SciSpace Literature Review is a breeze. The tool is designed to help researchers compare and contrast various papers, identify gaps in the current literature, and base their own studies on a solid evidence foundation — all in one single space.

To help you get started, here's a step-by-step guide on how to use SciSpace Search:

• Type in your query in the search bar.

2. Review the summarized insight for a quick and informative overview of what the top papers say about your query.

3. Ask follow-up questions to Copilot on summarized insights to gain a deeper understanding and clarify any doubts you may have.

4. Use search filters like publication type, year of publication, and PDF availability to narrow down the results table and find the most relevant papers for your research.

5. Use sort options to organize your search results table by relevance, date, or citation count and prioritize your reading list.

6. Add new or remove existing fields to customize the search results table to your specific needs.

7. Scroll horizontally and vertically to compare and contrast the findings from different papers to discover patterns, contradictions, gaps, or new perspectives.

8. If you find insights from a paper interesting, use Copilot to delve deeper into it, or simply click on the title to access the full text or metadata.

9. Star the papers you liked to generate more recommendations tailored to your preferences or to save them to your library for future reference.

10. Click on the minus button to remove papers that are not relevant to your research, helping to refine your search results and recommendations.

11. Click the three-dot menu to export the search results table to a CSV file for further analysis, collaboration, or to keep a record of your literature review process.

12. Click on the floppy disk icon to save your search settings and preferences, allowing you to easily pick up where you left off in future sessions.

13. Utilize the translate feature by clicking on the globe icon to conduct your literature review in your preferred language.

What makes SciSpace Literature Review so powerful?

Here are a few reasons why SciSpace Literature Review is your ideal companion for literature review:

Comprehensive repository: SciSpace presently holds more than 200 million research papers from across domains and disciplines. So, any keyword or query you type into the search bar is almost guaranteed to provide an extensive array of relevant articles for you to explore, analyze, and learn from. You can also upload your own papers or entire folders, allowing you to analyze and compare them against the vast collection in our database.

Customizable and advanced search options: Easily refine and sort your results by publication year, author, type, and other criteria to ensure you find the most pertinent information for your research. Additionally, you can sort your results by relevance, date, or citation count to manage your reading list effectively. The best part is that it lets you pinpoint insights from specific sections of a paper, like the abstract, methods, or results section, for focused and efficient exploration.

Smart summarization and in-depth analysis: For every query or keyword, you get both a high-level summary and detailed insights from each paper. You decide whether you want a quick overview or to dive deep into the specifics. Moreover, Copilot is always available to assist you, giving you the flexibility to ask follow-up questions and clarify any doubts instantly.

Seamless integration with Copilot AI assistant: This combination makes your literature review more interactive and proactive. While doing your literature review, if you come across an unfamiliar acronym, Copilot can quickly provide a definition. Found a complex concept in a research paper? Copilot can simplify it for you. You can even use Copilot's preset questions to engage with the literature in a more structured manner.

Multi-language support: Research is a global endeavor, and we believe language barriers should not limit your access to knowledge. This is why we offer a translation feature, allowing you to review, analyze, and understand papers in 75+ languages. You no longer have to worry about constantly switching between languages or translating scientific jargon. Everything you need is conveniently available in one place, in the language you are comfortable with. Additionally, you can communicate with Copilot in your preferred language.

Easy export and save options: After you've conducted your literature review, you can export your search results as a CSV file. This feature is particularly beneficial if you wish to share your findings with colleagues or want to keep a record of your search process for future reference. You can also save your search settings and preferences, enabling you to resume your literature review seamlessly in future sessions.

How to use SciSpace Literature Review?

Some examples of how SciSpace Literature Review can be used effectively in various research scenarios are:

• Identify gaps in the current body of knowledge by discovering trends and patterns in the literature.
• Conduct a systematic review or meta-analysis by quickly sourcing multiple high-quality studies and extracting relevant data.
• Explore interdisciplinary connections by analyzing research papers from various disciplines and fields.
• Evaluate the influence and impact of a particular research paper or author by analyzing citation counts, publication dates, and other relevant metrics.
• Enhance your understanding of a topic by generating a list of recommended papers based on your preferences.
• Keep track of the latest advancements and updates in your field of study by regularly using the search function.
• Prepare for a research presentation or discussion by gathering critical insights from various studies quickly.
• Develop a well-informed research proposal or thesis by leveraging the vast papers database and advanced search features.
• Collaborate with peers by sharing the CSV file of your search, enabling everyone to contribute and review collectively.

Final Thoughts

Academia is a demanding field that constantly requires you to stay on top of the latest studies, trends, and insights. But the sheer volume of papers published can make this a daunting task. However, your literature review process can become significantly more manageable and efficient with the right tools.

SciSpace Literature Review provides a comprehensive, accessible, and customizable platform that empowers you to conduct in-depth literature reviews efficiently, effectively, and collaboratively. Its advanced features and seamless integration with Copilot sets it apart as a literature review companion.

By using SciSpace Literature Review, you can save time, increase efficiency, and focus on the essential aspects of your work, ultimately contributing to scientific knowledge and discovery advancement.

Try SciSpace Literature Review today!

You might also like

Consensus GPT vs. SciSpace GPT: Choose the Best GPT for Research

How to Use AI Tools for Conducting a Literature Review

Elicit vs. SciSpace: AI research assistant for effortless literature review

• 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

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!