Please keep these differences in mind when exploring AI-powered academic search engines.
Library Subscribed AI-Assisted Databases
Dimensions (TAMU)
- Brings its linked multiple content types into a single place for improved global discovery and analysis.
- Two AI features: Summarization, and Research GPT which provides access only to its open-access collections.
Statista (TAMU)
- Contains international statistics, facts, and market data taken from free and proprietary sources
- AI features: Use its Research Assistant to generate insights from queried data.
TAMU: AI Tools or Services
------------------------------------------------------------------------------------------------------------------------------------------------------
Independent Subscription AI Tools (Library Subscription Not Available)
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
Semantic Reader
"Semantic Reader is an augmented reader with the potential to revolutionize scientific reading by making it more accessible and richly contextual." It "uses artificial intelligence to understand a document’s structure and merge it with the Semantic Scholar’s academic corpus, providing detailed information in context via tooltips and other overlays." <https://www.semanticscholar.org/product/semantic-reader>.
Skim Papers Faster
"Find key points of this paper using automatically highlighted overlays. Available in beta on limited papers for desktop devices only." <https://www.semanticscholar.org/product/semantic-reader>. Press on the pen icon to activate the highlights.
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>
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/>
Over 200-millions scholarly documents / Peer-reviewed / Subjects: Medical sciences, physics to social sciences and economics.Prompt “write me a paragraph about the impact of climate change on GDP with citations“
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.
How Does Litmaps Work?
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
-----------------------------------------------
ChatGPT
Increased risk of sudden infant death syndrome (SIDS)
Increased risk of premature birth
Increased risk of low birth weight
etc .......
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)
etc.....
[Press the Regenerate button to get more.]
(("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
Example- using ChatGPT4o to Extract sections from PDF
I am going to upload a PDF file. Please extract its Research Objectives, Hypotheses,Methodology and findings for me, and then save it into a text file.
ChatGPT40: Yes, you can upload the PDF..... The uploaded document appears to be a paper titled "......" I'll begin by searching for and extracting the relevant sections. Extracting Sections: Research Objectives and Hypotheses, Methodology, Results and Findings
Let me start with the extraction. The information has been saved into a text file. You can download it using the link below:Download Extracted_Info.txt
Bing Chat / Copilot
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.
Example: FINDING SIMILAR ARTICLES
Find similar articles like this one - [then paste in the abstract ]
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.
Example
You 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
Example
Please read this article and summarize it for 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.
Examples: Literature Review Matrix
Find five articles on a given topic first, and then use a prompt like this one:
Generate a 3-column table: 1st column list paper title, 2nd column list their research methods and 3rd column list their major findings.
You can also leverage ChatGPT 3.5 to convert your search results into a review matrix. Begin by searching an academic database and saving the outcomes in a plain text file. Next, extract only the needed information such as titles, authors, and abstracts, and incorporate them into your input prompt. Given ChatGPT's token limit for input, roughly about 1000 words, focus on extracting the necessary details. Should the file size be too large, consider splitting the task into several conversions and subsequently combining them.
CITING GENERATIVE AI
