literature review about ai

• 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

• Research AI Assistant is available in Dimensions Analytics (TAMU) and Statista (TAMU).
• See news about their AI Assistant (Beta): Web of Science , Scopus , Ebsco , ProQues t, OVID , Dimensions , JStor , Westlaw , and LexisNexis .

          ********** **********

Disclaimer:

• The guide is intended purely for informational purposes. It is advisable for you to independently evaluate these tools and their methods of use.

-------------------------------------------------------------------------------------------------------------------------------------------------------------

• https://www.openread.academy/
• Accessed institutionally by Harvard, MIT, University of Oxford, Johns Hopkins, Stanford, and more. ..
• AI-powered Academic Searching + Web Searching - Over 300 million papers and real-time web content.
• Trending and Topics - Browse them to find the latest hot papers. Use Topic to select specific fields and then see their trending.
• Each keyword search or AI query generates a synthesis report with citations. To adjust the search results, simply click on the Re-Generate button to refresh the report and the accompanied citations. After that click on Follow-Up Questions to go deeper into a specific area or subject.
• Use Paper Q&A to interact with a text directly. Examples: " What does this paper say about machine translation ?" ;  "What is C-1 in Fig.1?"
• When you read a paper, under Basic Information select any of the following tools to get more information: Basic Information > Related Paper Graph> Paper Espresso > Paper Q&A , and > Notes. The Related Paper Graph will present the related studies in a visual map with relevancy indication by percentage.
• Click on Translation to put a text or search results into another language.
• Read or upload a document and let Paper Espresso analyze it for you. It will organize the content into a standard academic report format for easy reference: Background and Context > Research Objectives and Hypotheses > Methodology > Results and Findings > Discussion and Interpretation > Contributions to the field > Structure and Flow > Achievements and Significance , and > Limitations and Future Work.  

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

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>  

• 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  

Scholar GPT - By awesomegpts.ai

• " Enhance research with 200M+ resources and built-in critical reading skills. Access Google Scholar, PubMed, JSTOR, Arxiv, and more, effortlessly ."
• Dialogue prompts suggested on the page: - Find the latest research about AI. - I'll provide a research paper link; Please analyze it. - I will upload a PDF paper; Use critical skills to read it. - Type "LS" to list my built-in critical reading list.
• To access it, in your ChatGPT account > Select " Explore GPTs > Scholar GPT
• 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: Jul 11, 2024 12:38 PM
• URL: https://tamu.libguides.com/c.php?g=1289555

• Advanced Search

Artificial intelligence in education: : A systematic literature review

New citation alert added.

This alert has been successfully added and will be sent to:

You will be notified whenever a record that you have chosen has been cited.

To manage your alert preferences, click on the button below.

New Citation Alert!

Please log in to your account

Information & Contributors

Bibliometrics & citations, view options, graphical abstract, recommendations, research on ethical issues of artificial intelligence in education.

The application of artificial intelligence technology in the field of education is becoming more and more extensive, and the ethical issues that come with it are common. The development of responsible and trustworthy artificial intelligence has ...

Mapping research strands of ethics of artificial intelligence in healthcare: A bibliometric and content analysis

The growth of artificial intelligence in promoting healthcare is rapidly progressing. Notwithstanding its promising nature, however, AI in healthcare embodies certain ethical challenges as well. This research aims to delineate the most ...

• This paper analyses scientific articles on the ethics of AI in healthcare domain.
• This analysis detects the hottest ethical challenges in the domain.
• It identifies the most influential elements such as authors and documents.

Use of Artificial Intelligence for Training: A Systematic Review

With the rapid advancement of artificial intelligence, it has been widely applied in various domains to assist training, including education, medical, automation, and industrial fields. The purpose of this study is to deep dive into the use of ...

Information

Published in.

Pergamon Press, Inc.

United States

Publication History

Author tags.

• Artificial intelligence
• Bibliometric analysis
• Literature review
• Content analysis
• Review-article

Contributors

Other metrics, bibliometrics, article metrics.

• 0 Total Citations
• 0 Total Downloads
• Downloads (Last 12 months) 0
• Downloads (Last 6 weeks) 0

View options

Login options.

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Share this publication link.

Copying failed.

Share on social media

Affiliations, export citations.

• Please download or close your previous search result export first before starting a new bulk export. Preview is not available. By clicking download, a status dialog will open to start the export process. The process may take a few minutes but once it finishes a file will be downloadable from your browser. You may continue to browse the DL while the export process is in progress. Download
• Download citation
• Copy citation

We are preparing your search results for download ...

We will inform you here when the file is ready.

Your file of search results citations is now ready.

Your search export query has expired. Please try again.

This manuscript presents a comprehensive review of the use of Artificial Intelligence (AI) in Systematic Literature Reviews (SLRs). A SLR is a rigorous and organised methodology that assesses and integrates prior research on a given topic. Numerous tools have been developed to assist and partially automate the SLR process. The increasing role of AI in this field shows great potential in providing more effective support for researchers, moving towards the semi-automatic creation of literature reviews. Our study focuses on how AI techniques are applied in the semi-automation of SLRs, specifically in the screening and extraction phases. We examine 21 leading SLR tools using a framework that combines 23 traditional features with 11 AI features. We also analyse 11 recent tools that leverage large language models for searching the literature and assisting academic writing. Finally, the paper discusses current trends in the field, outlines key research challenges, and suggests directions for future research. We highlight three primary research challenges: integrating advanced AI solutions, such as large language models and knowledge graphs, improving usability, and developing a standardised evaluation framework. We also propose best practices to ensure more robust evaluations in terms of performance, usability, and transparency. Overall, this review offers a detailed overview of AI-enhanced SLR tools for researchers and practitioners, providing a foundation for the development of next-generation AI solutions in this field.

Introduction

In this page, we report the tables we have developed when conducting our analysis on the Systematic Literature Review Tools.

Systematic Literature Review Tools analysed through AI and Generic Features

Screening phase of systematic literature review tools analysed through ai features.

• Extraction Phase of Systematic Literature Review Tools analysed through AI Features
• Systematic Literature Review Tools analysed based on AI Features

Figures of the paper

Prisma checklist.

• Codebase Snowballing

How to cite

In this section, we report three tables that describe the 21 systematic literature review tools examined according to both generic and AI-based features. In Section 1.1 and Section 1.2 , we present the analysis of the AI features for the screening and the extraction phases, respectively. In Section 1.3 , we report the analysis of the tools according to the generic features. A copy of these tables is persistently available on ORKG.

-: No information available

Extraction phase of Systematic Literature Review Tools analysed through AI Features

Systematic Literature Review Tools analysed based on General Features

-: No information available NA: Not applicable because the tools are specifically for extraction

In this section we attach all the figures of the mauscript in high defininition (300DPI).

In the following table we report our PRISMA checklist, using the model from "Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ 2021;372:n71. doi: 10.1136/bmj.n71".

Here is the codebase we developed for the snowballing search on Semantic Scholar.

F. Bolaños Burgos, A. Salatino, F. Osborne, and E. Motta. Artificial intelligence for systematic literature reviews: Opportunities and challenges. Submitted to Artificial Intelligence Review, 2024.

This work is licensed under CC BY 4.0

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
• CORRESPONDENCE
• 16 July 2024

Generative AI makes for better scientific writing — but beware the pitfalls

• Zhongkai Liao 0 &
• Congcong Zhang 1

Second Affiliated Hospital of Hainan Medical University, Haikou, China.

You can also search for this author in PubMed   Google Scholar

Xiangya School of Medicine of Central South University, Changsha, China.

Dritjon Gruda’s Careers Column on his use of the chatbot ChatGPT offers valuable insights into the benefits of integrating generative artificial intelligence (AI) into academic writing, editing and peer-review processes (see Nature https://doi.org/gtzb44; 2024 ).

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

Prices may be subject to local taxes which are calculated during checkout

Nature 631 , 505 (2024)

doi: https://doi.org/10.1038/d41586-024-02319-3

Competing Interests

The authors declare no competing interests.

Related Articles

• Machine learning
• Scientific community

Why you should perform a premortem on your research

Career Column 24 JUL 24

So you got a null result. Will anyone publish it?

News Feature 24 JUL 24

A stroke derailed my academic career. Now I’m getting back on track

Career Column 23 JUL 24

Three ways AI is changing the 2024 Olympics for athletes and fans

News Explainer 25 JUL 24

AI is vulnerable to attack. Can it ever be used safely?

Outlook 25 JUL 24

DeepMind hits milestone in solving maths problems — AI’s next grand challenge

News 25 JUL 24

V. Craig Jordan obituary: pharmacologist who revolutionized breast cancer treatments

Obituary 25 JUL 24

India budget: Modi bets big on nuclear energy and space

Postdoctoral Research Scientist

Computational Postdoctoral Research Scientist in Neurodegenerative Disease

New York City, New York (US)

Columbia University Department of Pathology

Associate or Senior Editor (Chemical Engineering), Nature Sustainability

Associate or Senior Editor (Chemical engineering), Nature Sustainability Locations: New York, Philadelphia, Berlin, or Heidelberg Closing date: Aug...

Springer Nature Ltd

Postdoctoral Research Scientist - Mouse Model

The Stavros Niarchos Foundation Center for Precision Psychiatry & Mental Health is seeking a Postdoctoral Research Scientist for the Mouse Model.

Columbia University Irving Medical Center / Vagelos College of Physicians and Surgeons

Postdoctoral Research Scientist - IPSC Program

The Stavros Niarchos Foundation Center for Precision Psychiatry & Mental Health is seeking a Postdoctoral Research Scientist - IPSC Program.

Postdoctoral Research Scientist - Xenotransplantation

The Stavros Niarchos Foundation Center for Precision Psychiatry & Mental Health is seeking a Postdoctoral Research Scientist -Xentotransplantation.

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

A free, AI-powered research tool for scientific literature

• Sossina M. Haile
• Classical Economics
• Riemann Hypothesis

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.

Literature Reviews

• Artificial intelligence (AI) tools
• Getting started
• Types of reviews
• 1. Define your research question
• 2. Plan your search
• 3. Search the literature
• 4. Organize your results
• 5. Synthesize your findings
• 6. Write the review

Introduction to AI

Research rabbit, copilot (powered by chatgpt4).

• Thompson Writing Studio This link opens in a new window
• Need to write a systematic review? This link opens in a new window

Contact a Librarian

Ask a Librarian

Generative AI tools have been receiving a lot of attention lately because they can create content like text, images, and music. These tools employ machine learning algorithms that can produce unique and sometimes unexpected results. Generative AI has opened up exciting possibilities in different fields, such as language models like GPT and image generators.

However, students need to approach these tools with awareness and responsibility. Here are some key points to consider:

Novelty and Creativity : Generative AI tools can produce content that is both innovative and unexpected. They allow users to explore new ideas, generate unique artworks, and even compose original music. This novelty is one of their most exciting aspects.

Ethical Considerations : While generative AI offers creative potential, it also raises ethical questions. Students should be aware of potential biases, unintended consequences, and the impact of their generated content. Responsible use involves considering the broader implications.

Academic Integrity : When using generative AI tools for academic purposes, students should consult their instructors. Policies regarding the use of AI-generated content may vary across institutions. Always seek guidance to ensure compliance with academic integrity standards.

In summary, generative AI tools are powerful and fascinating, but students should approach them thoughtfully, seek guidance, and adhere to institutional policies. Please refer to the Duke Community Standard  for questions related to ethical AI use.

Looking for a tool that isn't listed here? Let us know about it!

Research Rabbit is a literature mapping tool that takes one paper and performs backward- and forward citation searching in addition to recommending "similar work." It scans the Web for publicly available content to build its "database" of work.

Best suited for...

Disciplines whose literature is primarily published in academic journals.

Considerations

• Integrates with Zotero
• Works mostly with just journal articles
• Potential for bias in citation searching/mapping

»   researchrabbit.ai   «

What is it?

Elicit is a tool that semi-automates time-intensive research processes, such as summarizing papers , extracting data , and synthesizing information . Elicit pulls academic literature from Semantic Scholar , an academic search engine that also uses machine learning to summarize information.

Empirical research (i.g., the sciences, especially biomedicine).

• Both free and paid versions
• Doesn't work well in identifying facts or in theoretical/non-empirical research (e.g., the humanities)
• Potential biases in the natural language processing (NLP) algorithms
• Summarized information and extracted data will still need to be critically analyzed and verified for accuracy by the user

»   elicit.com   «

Think of Consensus as ChatGPT for research! Consensus is "an AI-powered search engine designed to take in research questions, find relevant insights within research papers, and synthesize the results using the power of large language models" ( Consensus.app ).  Consensus runs its language model over its entire body of scientific literature (which is sourced from Semantic Scholar ) and extracts the “key takeaway” from every paper.

The social sciences and sciences (non-theoretical disciplines).

• Free and paid versions
• Similar to Elicit, Consensus should not be used to ask questions about basic facts
• Consensus recommends that you ask questions related to research that has already been conducted by scientists
• Potential for biases in the input data from participants

»   consensus.app   «

Dubbed the "AI-powered Swiss Army Knife for information discovery," Perplexity is used for answering questions (including basic facts, a function that many other AI tools are not adept at doing), exploring topics in depth utilizing Microsoft's Copilot, organizing your research into a library, and interacting with your data (including asking questions about your files).

Perplexity has wide-reaching applications and could be useful across disciplines.

• Free and paid pro versions (the pro version utilizes Microsoft's Copilot AI tool)
• Available in desktop, iOS, and Android apps
• See  Perplexity's blog for more info
• Your personal information and data on how you use the tool are stored for analytical purposes (however, this feature can be turned off in settings)
• Features a browser plug-in, Perplexity Companion , that is essentially a blend of Google and ChatGPT

»   perplexity.ai   «

Did you know that as Duke faculty, staff, and students, we have free access to ChatGPT4 via Microsoft Copilot ?

Log in with your Duke credentials to start using it today.

The OG of generative AI tools, ChatGPT-4 is the latest iteration of the popular chatbot, answering questions and generating text that sounds like it was written by a human. While not a replacement for conducting research, it can be helpful when it comes to brainstorming topics or research questions and also as a writing tool (rewriting or paraphrasing content, assessing tone, etc.).

All users across all disciplines.

• ChatGPT-3.5 is the default version of free and paid-tier chat users.
• Since it can't verify its sources, be wary of hallucinations (or made-up citations) that can look very real.
• It is not 100% accurate ! While ChatGPT-4 is touted as being 40% more accurate than its predecessor, users are still expected to verify the information generated by it.
• There is always the potential for bias since ChatGPT was trained on a massive dataset of websites, articles, books, etc. (much of which is inherently biased since it was created by humans).

For ChatGPT-4 (access provided by Duke and requires login) »   copilot.microsoft.com   «

For ChatGPT-3.5 (free) »   chat.openai.com   «

• << Previous: 6. Write the review
• Next: Thompson Writing Studio >>
• Last Updated: Jul 16, 2024 10:20 AM
• URL: https://guides.library.duke.edu/litreviews

Services for...

• Faculty & Instructors
• Graduate Students
• Undergraduate Students
• International Students
• Patrons with Disabilities

• Harmful Language Statement
• Re-use & Attribution / Privacy
• Support the Libraries

Information

• Author Services

Initiatives

You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.

All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess .

Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.

Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.

Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.

Original Submission Date Received: .

• Active Journals
• Find a Journal
• Proceedings Series
• For Authors
• For Reviewers
• For Editors
• For Librarians
• For Publishers
• For Societies
• For Conference Organizers
• Open Access Policy
• Institutional Open Access Program
• Special Issues Guidelines
• Editorial Process
• Research and Publication Ethics
• Article Processing Charges
• Testimonials
• Preprints.org
• SciProfiles
• Encyclopedia

Article Menu

• Subscribe SciFeed
• Recommended Articles
• Google Scholar
• on Google Scholar
• Table of Contents

Find support for a specific problem in the support section of our website.

Please let us know what you think of our products and services.

Visit our dedicated information section to learn more about MDPI.

JSmol Viewer

Artificial intelligence as a disruptive technology—a systematic literature review.

1. Introduction

2. materials and methods.

• First exclusion: ○ Document types—the Editorial Materials and Meeting Abstracts were removed (WoS—38, S—42), leaving 124 (WoS) + 142 (S) = 266 papers; ○ All publishers with only 1 article, as we considered that they did not have a serious approach toward this topic, were removed (WoS—20, S—23), leaving 104 (WoS) + 119 (S). Further, at this stage, the intermediary results (1) were merged into the same file, resulting in 223 articles.
• Second exclusion: ○ With the support of EndNote (used for reference management), it was possible to identify duplicate records (196) originating from the two databases and retain only 1 entry (98). In this manner, we obtained the intermediary results (2), with a total of 125 references.
• Third exclusion: ○ The remaining list was evaluated for relevance based on title, keyword, and abstract analysis, and the articles that did not fit the purpose of the research were eliminated (−28), leaving a total of 97 papers included in the study.

3.1. AI as a Disruptive Technology in Healthcare (Medicine)

3.1.1. disruptive features in the applications to surgery, 3.1.2. disruptive features in the applications to healthcare, 3.2. ai as a disruptive technology in business—logistics and transportation and the labor market, 3.2.1. logistics, 3.2.2. labor market, 3.3. ai as a disruptive technology in agriculture, 3.3.1. smart farming, 3.3.2. digital twins, 3.3.3. the fourth industrial revolution (4ir), 3.4. ai as a disruptive technology in education, 3.5. ai as a disruptive technology with respect to urban development—society, smart cities, and smart government, 3.5.1. disruptive technology’s impact on society, 3.5.2. smart cities, 3.5.3. smart government, 4. discussion and conclusions.

• Enhanced diagnosis, as AI algorithms can examine a large number of medical data to help clinicians make more accurate diagnoses, thus minimizing the possibility of misdiagnosis;
• Personalized medicine, since by using a patient’s particular medical history and genetic data, AI can aid the development of individualized treatment approaches;
• Superior patient outcomes, as AI may be used to track patients, anticipate future health difficulties, and alert medical professionals to take preventative action before significant health issues arise;
• Expedite drug development, because AI can analyze massive volumes of data to hasten the process of developing new drugs and bringing them to market;
• Improved clinical trials, due to the fact that data from clinical trials may be analyzed using AI algorithms, thus assisting in the selection of the most efficient therapies and enhancing patient results.
• The development of AI in healthcare creates ethical issues, such as the issue of responsibility in situations of misdiagnosis or treatment suggestions;
• Limited clinical validity poses a serious problem, because in certain complicated medical situations, AI algorithms may not be as accurate as human specialists and may not be completely verified for assessing all medical disorders;
• Healthcare professionals and patients who are suspicious about the accuracy and dependability of the technology can be resistant to the adoption of AI in the industry.
• For improved supply chain management, AI may aid routing, scheduling, and delivery optimization, which lowers transportation costs and increases delivery times;
• Transportation safety may be improved by using AI to track and improve driver behavior, reduce collisions, and increase road safety;
• AI can enhance logistics efficiency, as it may be used to improve inventory management, optimize storage and picking procedures, and expedite warehouse operations;
• AI is transforming the labor sector by replacing many old manual jobs while also opening up new career prospects in programming and data analysis;
• AI may improve customer experience as it can be used to offer updates on tracking and delivery in real-time, thereby reducing wait times and raising satisfaction;
• AI may aid the maximization of fuel use and the cutting of emissions through effective vehicle scheduling and routing and thus contribute to minimized environmental impacts;
• Many laborious and repetitive tasks will be automated, which may result in fewer jobs and employment possibilities, particularly in sectors such as logistics and transportation;
• As the demand for more high-skilled positions in AI and data analysis increases and fewer low-skilled occupations are automated, the rising usage of AI may worsen already-existing income discrepancies;
• The widespread usage of autonomous cars may result in substantial social and cultural changes, such as the loss of individual driving abilities and the demise of the automobile culture.
• Improved agricultural yields and less waste are possible with the use of AI, which may help farmers optimize planting, irrigation, and fertilization;
• Better resource management may help farmers conserve energy, water, and other resources while decreasing waste and enhancing sustainability;
• Enhanced food safety can be enforced by tracking the whole food production chain from farm to table, while AI can assist in the identification and prevention of food-borne diseases;
• AI can provide real-time analysis of crop, soil, and weather variables, thus enabling farmers to make educated decisions;
• Predictive maintenance may reduce downtime and boost production by predicting when machines and equipment need maintenance.
• AI systems are not immune to technical glitches or malfunctions, and the agricultural sector might suffer significantly as a result, leading to crop losses and possible food shortages;
• The usage of AI in agriculture may have unforeseen environmental effects, including increased pesticide and herbicide use, degraded soil, and the loss of biodiversity.
• A decrease in dropout rates and improved student results due to AI’s ability to detect students’ areas of need and offer focused support;
• Education that is customized to each student’s requirements, interests, and learning preferences may be achieved by using AI to deliver personalized learning experiences for students;
• Improved assessment and feedback due to AI’s ability to automate, enhance, and optimize the grading and feedback process and provide students faster, more precise, and more thorough feedback on their work;
• Lifelong learning is possible because of AI, which can help people continue to learn and advance their expertise.
• Education quality may suffer due to the usage of AI in the classroom when human interaction, creativity, and critical thinking abilities are substituted by automated procedures;
• A lack of critical thinking abilities may be precipitated by AI because the use of AI-powered tools and resources may lessen the necessity for critical thinking and problem-solving abilities, which may retard the development of these skills among students;
• The dependence on technology due to an overreliance on AI in the classroom may result in a lack of creativity, independence, and decision-making abilities, which will reduce students’ capacity to think and work independently.
• An increase in transparency, as by using AI to render governmental processes more open and accountable, individuals will be able to better understand how choices are made;
• Enhanced fraud detection, since AI may be used to identify and stop corruption and fraud in government systems, thus increasing public confidence in these organizations;
• Better resource allocation, because governmental organizations may use AI to more effectively direct resources, including money and staff, to the areas where they are most needed;
• The introduction of predictive analytics, as through the use of AI, government agencies may employ predictive analytics to proactively address prospective concerns before they become problems.
• Privacy issues—Government entities frequently deploy AI algorithms that rely on substantial volumes of personal data, which raises privacy concerns regarding how these data are gathered, kept, and used;
• Lack of transparency—AI technologies employed by government agencies may be opaque, making it difficult for the public to comprehend how and why choices are being made;
• The employment of AI in governmental affairs may result in greater control and surveillance, which may have detrimental effects on free expression and civil rights;
• When an AI system utilized by a government errs or causes harm, it may be challenging to pinpoint the culprit, which results in a lack of accountability.

Author Contributions

Data availability statement, conflicts of interest.

• Bower, L.J.; Christensen, M.C. Disruptive technologies: Catching the wave. Har. Buss. Rev. 1995 , 73 , 43–53. [ Google Scholar ]
• Christensen, C.M.; Bower, J.L. Customer power, strategic investment, and the failure of leading firms. Strateg. Manag. J. 1996 , 17 , 197–218. [ Google Scholar ]
• Christensen, C.M. The Innovator’s Dilemma: When New Technologies Cause Great Firms to Fail ; Harvard Business School Press: Boston, MA, USA, 1997; 179p. [ Google Scholar ]
• O’Connor, S.; Sidorko, P. Chapter 2—The complexities of our informational environment. In Imagine Your Library’s Future ; Chandos Publishing: Oxford, UK, 2010; pp. 33–60. [ Google Scholar ]
• Laukyte, M. Disruptive Technologies and the Sport Ecosystem: A Few Ethical Questions. Philosophies 2020 , 5 , 24. [ Google Scholar ] [ CrossRef ]
• Jekov, B.; Petkova, P.; Parusheva, Y.; Shoikova, E. Disruptive Technologies—Artificial Intelligence and Blockchain in Education. In Proceedings of the 11th Annual International Conference of Education, Research and Innovation (ICERI), Seville, Spain, 7–9 November 2022; pp. 6784–6793. [ Google Scholar ]
• Bongomin, O.; Ocen, G.G.; Nganyi, E.O.; Musinguzi, A.; Omara, T. Exponential Disruptive Technologies and the Required Skills of Industry 4.0. J. Eng. 2020 , 2020 , 4280156. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Hernández, R. World Standards Day 2018 Puts the Spotlight on the Fourth Industrial Revolution. Available online: https://www.iso.org/news/ref2333.html (accessed on 19 January 2023).
• Bird, K. Four Trends Will Impact ISO’s Future Strategy. Available online: https://www.iso.org/news/ref2436.html (accessed on 19 January 2023).
• Bublitz, F.M.; Oetomo, A.; Sahu, K.S.; Kuang, A.; Fadrique, L.X.; Velmovitsky, P.E.; Nobrega, R.M.; Morita, P.P. Disruptive Technologies for Environment and Health Research: An Overview of Artificial Intelligence, Blockchain, and Internet of Things. Int. J. Environ. Res. Public Health 2019 , 16 , 3847. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Chang, N.; Zhang, Y.; Lu, D.; Zheng, X.; Xue, J. Is a Disruptive Technology Disruptive? The Readiness Perspective Based on TOE. In Proceedings of the 2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Singapore, 14–17 December 2020; pp. 893–897. [ Google Scholar ]
• Cartaxo, B.; Pinto, G.; Soares, S. The role of rapid reviews in supporting decision-making in software engineering practice. In Proceedings of the 22nd International Conference on Evaluation and Assessment in Software Engineering—EASE’18, Christchurch, New Zealand, 28–29 June 2018. [ Google Scholar ]
• Christensen, C.M.; McDonald, R.; Altman, E.J.; Palmer, J.E. Disruptive innovation: An intellectual history and directions for future research. J. Manag. Stud. 2018 , 55 , 1043–1078. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Popescul, D.; Radu, L.D.; Păvăloaia, V.D.; Georgescu, M.R. Psychological Determinants of Investor Motivation in Social Media-Based Crowdfunding Projects: A Systematic Review. Front. Psychol. 2020 , 11 , 588121. [ Google Scholar ] [ CrossRef ]
• Radu, L.D. Disruptive Technologies in Smart Cities: A Survey on Current Trends and Challenges. Smart Cities 2020 , 3 , 1022–1038. [ Google Scholar ] [ CrossRef ]
• VOSViewer. Visualizing Scientific Landscapes. Available online: https://www.vosviewer.com/features/highlights (accessed on 20 July 2022).
• Basmmi, A.B.M.N.; Abd Halim, S.; Saadon, N.A. Comparison of web services for sentiment analysis in social networking sites. In Proceedings of the IOP Conference Series: Materials Science and Engineering, Tangerang, Indonesia, 18–20 November 2020. [ Google Scholar ]
• Abdullah, N.S.D.; Zolkepli, I.A. Sentiment Analysis of Online Crowd Input towards Brand Provocation in Facebook, Twitter, and Instagram. In Proceedings of the International Conference on Big Data and Internet of Thing—BDIOT2017, London, UK, 20–22 December 2017. [ Google Scholar ]
• Byrne, M.; O’Malley, L.; Glenny, A.M.; Pretty, I.; Tickle, M. Assessing the reliability of automatic sentiment analysis tools on rating the sentiment of reviews of NHS dental practices in England. PLoS ONE 2021 , 16 , e0259797. [ Google Scholar ] [ CrossRef ]
• Saura, J.R.; Reyes-Menendez, A.; Alvarez-Alonso, C. Do Online Comments Affect Environmental Management? Identifying Factors Related to Environmental Management and Sustainability of Hotels. Sustainability 2018 , 10 , 3016. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Pahuriray, A.V.; Basanta, J.D.; Arroyo, J.C.T.; Delima, A.J.P. Flexible Learning Experience Analyzer (FLExA): Sentiment Analysis of College Students through Machine Learning Algorithms with Comparative Analysis using WEKA. Int. J. Emerg. Technol. Adv. Eng. 2022 , 12 , 1–15. [ Google Scholar ] [ CrossRef ]
• Stoiber, C.; Walchshofer, C.; Pohl, M.; Potzmann, B.; Grassinger, F.; Stitz, H.; Streit, M.; Aigner, W. Comparative evaluations of visualization onboarding methods. Vis. Inform. 2022 , 6 , 34–50. [ Google Scholar ] [ CrossRef ]
• Zhuang, Y. Emotional analysis of sentences based on machine learning. In Big Data Analytics for Cyber-Physical System in Smart City ; Advances in Intelligent Systems and Computing; Atiquzzaman, M., Yen, N., Xu, Z., Eds.; Springer: Singapore, 2020; pp. 813–820. [ Google Scholar ] [ CrossRef ]
• Elangovan, K.; JasmineRani, L.P.; Karthikeyan, M.P.; Therasa, M. Analysis of Social Network with Ontology and Deep Sentiment Durability Detection (SSD) Model for Green Community. J. Green Eng. 2020 , 10 , 2661–2677. [ Google Scholar ]
• Monkeylearn. No-Code Text Analytics. Available online: https://monkeylearn.com (accessed on 20 July 2022).
• Contreras, D.; Wilkinson, S.; Alterman, E.; Hervás, J. Accuracy of a pre-trained sentiment analysis (SA) classification model on tweets related to emergency response and early recovery assessment: The case of 2019 Albanian earthquake. Nat. Hazards 2022 , 113 , 403–421. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Contreras, D.; Wilkinson, S.; Balan, N.; James, P. Assessing post-disaster recovery using sentiment analysis: The case of L’Aquila. Earthq. Spectra 2022 , 38 , 81–108. [ Google Scholar ] [ CrossRef ]
• Sadriu, S.; Nuci, K.P.; Imran, A.S.; Uddin, I.; Sajjad, M. An Automated Approach for Analysing Students Feedback Using Sentiment Analysis Techniques. In Mediterranean Conference on Pattern Recognition and Artificial Intelligence ; Springer International Publishing: Cham, Switzerland, 2021; pp. 228–239. [ Google Scholar ]
• Bredava, A. A Guide to Sentiment Analysis: What Is It and How Does It Work? Available online: https://awario.com/blog/sentiment-analysis (accessed on 15 January 2023).
• Ryman-Tubb, N.F.; Krause, P.; Garn, W. How Artificial Intelligence and machine learning research impacts payment card fraud detection: A survey and industry benchmark. Eng. Appl. Artif. Intell. 2018 , 76 , 130–157. [ Google Scholar ] [ CrossRef ]
• Aria, M.; Cuccurullo, C. Bibliometrix: An R-tool for comprehensive science mapping analysis. J. Informetr. 2017 , 11 , 959–975. [ Google Scholar ] [ CrossRef ]
• International Organization for Standardization. ISO Standardization Foresight Framework—Trend Report 2022. Available online: https://www.iso.org/files/live/sites/isoorg/files/store/en/PUB100470.pdf (accessed on 19 January 2023).
• Dal Mas, F.; Piccolo, D.; Cobianchi, L.; Edvinsson, L.; Presch, G.; Massaro, M.; Skrap, M.; Vajana, A.F.D.; D’Auria, S.D.S.; Bagnoli, C. The Effects of Artificial Intelligence, Robotics, and Industry 4.0 Technologies. Insights from the Healthcare Sector. In Proceedings of the European Conference on the Impact of Artificial Intelligence and Robotics (ECIAIR), EM Normandie Business Sch, Oxford, UK, 31 Octorber–1 November 2022; pp. 88–95. [ Google Scholar ]
• Manickam, P.; Mariappan, S.A.; Murugesan, S.M.; Hansda, S.; Kaushik, A.; Shinde, R.; Thipperudraswamy, S.P. Artificial Intelligence (AI) and Internet of Medical Things (IoMT) Assisted Biomedical Systems for Intelligent Healthcare. Biosensors 2022 , 12 , 562. [ Google Scholar ] [ CrossRef ]
• Kelly, J.T.; Collins, P.F.; McCamley, J.; Ball, L.; Roberts, S.; Campbell, K.L. Digital disruption of dietetics: Are we ready? J. Hum. Nutr. Diet. 2021 , 34 , 134–146. [ Google Scholar ] [ CrossRef ]
• Joda, T.; Yeung, A.W.K.; Hung, K.; Zitzmann, N.U.; Bornstein, M.M. Disruptive Innovation in Dentistry: What It Is and What Could Be Next. J. Dent. Res. 2021 , 100 , 448–453. [ Google Scholar ] [ CrossRef ]
• Ahmad, P.; Alam, M.; Aldajani, A.; Alahmari, A.; Alanazi, A.; Stoddart, M.; Sghaireen, M. Dental Robotics: A Disruptive Technology. Sensors 2021 , 21 , 3308. [ Google Scholar ] [ CrossRef ]
• McBee, M.P.; Wilcox, C. Blockchain Technology: Principles and Applications in Medical Imaging. J. Digit. Imaging 2020 , 33 , 726–734. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Rasouli, J.J.; Shao, J.N.; Neifert, S.; Gibbs, W.N.; Habboub, G.; Steinmetz, M.P.; Benzel, E.; Mroz, T.E. Artificial Intelligence and Robotics in Spine Surgery. Glob. Spine J. 2021 , 11 , 556–564. [ Google Scholar ] [ CrossRef ] [ PubMed ] [ Green Version ]
• Dorweiler, B.; Wegner, M.; Salem, O.; Murtaja, A.; Schäfers, J.F.; Oberhuber, A. Innovation, disruptive technologies and transformation in vascular surgery. Gefasschirurgie 2022 , 27 , 561–568. [ Google Scholar ] [ CrossRef ]
• Mohanty, K.; Subiksha, S.; Kirthika, S.; Bh, S.; Sokkanarayanan, S.; Bose, P.; Sathiyanarayanan, M.; IEEE. Opportunities of Adopting AI-Powered Robotics to Tackle COVID-19. In Proceedings of the International Conference on COMmunication Systems and NETworkS (COMSNETS), Bangalore, India, 5–9 January 2022; pp. 703–708. [ Google Scholar ]
• Jabarulla, M.Y.; Lee, H.N. A Blockchain and Artificial Intelligence-Based, Patient-Centric Healthcare System for Combating the COVID-19 Pandemic: Opportunities and Applications. Healthcare 2021 , 9 , 1019. [ Google Scholar ] [ CrossRef ]
• Saraswat, D.; Bhattacharya, P.; Verma, A.; Prasad, V.K.; Tanwar, S.; Sharma, G.; Bokoro, P.N.; Sharma, R. Explainable AI for Healthcare 5.0: Opportunities and Challenges. IEEE Access 2022 , 10 , 84486–84517. [ Google Scholar ] [ CrossRef ]
• Mesko, B.; Hetenyi, G.; Gyorffy, Z. Will artificial intelligence solve the human resource crisis in healthcare? BMC Health Serv. Res. 2018 , 18 , 545. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Maliha, G.; Gerke, S.; Cohen, G.; Parikh, R.B. Artificial Intelligence and Liability in Medicine: Balancing Safety and Innovation. Milbank Q. 2021 , 99 , 629–647. [ Google Scholar ] [ CrossRef ]
• Khatab, Z.; Yousef, G.M. Disruptive innovations in the clinical laboratory: Catching the wave of precision diagnostics. Crit. Rev. Clin. Lab. Sci. 2021 , 58 , 546–562. [ Google Scholar ] [ CrossRef ]
• Brunelle, F.; Brunelle, P. Artificial Intelligence and Medical Imaging: Definition, State of the Art and Perspectives. Bull. Acad. Natl. Med. 2019 , 203 , 683–687. [ Google Scholar ]
• Garbuio, M.; Lin, N. Artificial Intelligence as a Growth Engine for Health Care Startups: Emerging Business Models. Calif. Manag. Rev. 2019 , 61 , 59–83. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Prakash, S.; Balaji, J.N.; Joshi, A.; Surapaneni, K.M. Ethical Conundrums in the Application of Artificial Intelligence (AI) in Healthcare—A Scoping Review of Reviews. J. Pers. Med. 2022 , 12 , 1914. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Mesko, B. Future Directions of Digital Health. In Digital Health: Scaling Healthcare to the World ; Rivas, H., Wac, K., Eds.; Springer: Berlin/Heidelberg, Germany, 2018; pp. 339–363. [ Google Scholar ] [ CrossRef ]
• Ojo, A. Next Generation Government—Hyperconnected, Smart and Augmented. In Proceedings of the 20th IFIP WG 5.5 Working Conference on Virtual Enterprises (PRO-VE), Turin, Italy, 23–25 September 2019; pp. 285–294. [ Google Scholar ]
• Ljepava, N. AI-Enabled Marketing Solutions in Marketing Decision Making: AI Application in Different Stages of Marketing Process. TEM J. 2022 , 11 , 1308–1315. [ Google Scholar ] [ CrossRef ]
• Wiegandt, D. Blockchain and Smart Contracts and the Role of Arbitration. J. Int. Arbitr. 2022 , 39 , 671–690. [ Google Scholar ] [ CrossRef ]
• Dong, C.W.; Akram, A.; Andersson, D.; Arnas, P.O.; Stefansson, G. The impact of emerging and disruptive technologies on freight transportation in the digital era: Current state and future trends. Int. J. Logist. Manag. 2021 , 32 , 386–412. [ Google Scholar ] [ CrossRef ]
• Noor, A. Adoption of Blockchain Technology Facilitates a Competitive Edge for Logistic Service Providers. Sustainability 2022 , 14 , 15543. [ Google Scholar ] [ CrossRef ]
• Ugochukwu, N.A.; Goyal, S.B.; Rajawat, A.S.; Islam, S.M.N.; He, J.; Aslam, M. An Innovative Blockchain-Based Secured Logistics Management Architecture: Utilizing an RSA Asymmetric Encryption Method. Mathematics 2022 , 10 , 4670. [ Google Scholar ] [ CrossRef ]
• Zondervan, N.A.; Tolentino-Zondervan, F.; Moeke, D. Logistics Trends and Innovations in Response to COVID-19 Pandemic: An Analysis Using Text Mining. Processes 2022 , 10 , 2667. [ Google Scholar ] [ CrossRef ]
• Hong, Z.F.; Zhang, H.Y.; Gong, Y.M.; Yu, Y.G. Towards a multi-party interaction framework: State-of-the-art review in sustainable operations management. Int. J. Prod. Res. 2022 , 60 , 2625–2661. [ Google Scholar ] [ CrossRef ]
• Yu, H. Modeling a remanufacturing reverse logistics planning problem: Some insights into disruptive technology adoption. Int. J. Adv. Manuf. Technol. 2022 , 123 , 4231–4249. [ Google Scholar ] [ CrossRef ]
• Jia, W.; Wang, S.; Xie, Y.; Chen, Z.; Gong, K. Disruptive technology identification of intelligent logistics robots in AIoT industry: Based on attributes and functions analysis. Syst. Res. Behav. Sci. 2022 , 39 , 557–568. [ Google Scholar ] [ CrossRef ]
• Cukier, W. Disruptive processes and skills mismatches in the new economy Theorizing social inclusion and innovation as solutions. J. Glob. Responsib. 2019 , 10 , 211–225. [ Google Scholar ] [ CrossRef ]
• Oosthuizen, R.M. The Fourth Industrial Revolution—Smart Technology, Artificial Intelligence, Robotics and Algorithms: Industrial Psychologists in Future Workplaces. Front. Artif. Intell. 2022 , 5 , 913168. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Khatri, S.; Pandey, D.K.; Penkar, D.; Ramani, J. Impact of Artificial Intelligence on Human Resources. In Data Management, Analytics and Innovation ; Advances in Intelligent Systems and Computing; Sharma, N., Chakrabarti, A., Balas, V., Eds.; Springer: Singapore, 2019. [ Google Scholar ]
• Burden, K. Impact of disruptive technologies on sourcing and outsourcing transactions. Comput. Law Secur. Rev. 2018 , 34 , 886–889. [ Google Scholar ] [ CrossRef ]
• Miklosik, A.; Evans, N. Impact of Big Data and Machine Learning on Digital Transformation in Marketing: A Literature Review. IEEE Access 2020 , 8 , 101284–101292. [ Google Scholar ] [ CrossRef ]
• Koizumi, S. The Light and Shadow of the Fourth Industrial Revolution. In Innovation beyond Technology: Science for Society and Interdisciplinary Approaches ; Lechevalier, S., Ed.; Springer: Berlin/Heidelberg, Germany, 2019; pp. 63–86. [ Google Scholar ] [ CrossRef ]
• Rosales, M.A.; Magsumbol, J.A.V.; Palconit, M.G.B.; Culaba, A.B.; Dadios, E.P. Artificial Intelligence: The Technology Adoption and Impact in the Philippines. In Proceedings of the IEEE 12th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), Manila, Philippines, 3–7 December 2020. [ Google Scholar ]
• Anitha, J.; Saranya, N. Cassava Leaf Disease Identification and Detection Using Deep Learning Approach. Int. J. Comput. Commun. Control 2022 , 17 , 1–7. [ Google Scholar ] [ CrossRef ]
• Ortola, A. Unlocking the full potential of artificial intelligence in PH. Philippine Daily Inquirer , 24 June 2019. [ Google Scholar ]
• Karimanzira, D.; Rauschenbach, T. An intelligent management system for aquaponics. at-Automatisierungstechnik 2021 , 69 , 345–350. [ Google Scholar ] [ CrossRef ]
• Jacobs, M.; Remus, A.; Gaillard, C.; Menendez, H.M.; Tedeschi, L.O.; Neethirajan, S.; Ellis, J.L. ASAS-NANP symposium: Mathematical modeling in animal nutrition: Limitations and potential next steps for modeling and modelers in the animal sciences. J. Anim. Sci. 2022 , 100 , skac132. [ Google Scholar ] [ CrossRef ]
• De Bernardi, P.; Azucar, D.; Forliano, C.; Franco, M. Innovative and Sustainable Food Business Models. In Innovation in Food Ecosystems: Entrepreneurship for a Sustainable Future ; Springer: Berlin/Heidelberg, Germany, 2020; pp. 189–221. [ Google Scholar ] [ CrossRef ]
• Neethirajan, S.; Kemp, B. Digital Twins in Livestock Farming. Animals 2021 , 11 , 1008. [ Google Scholar ] [ CrossRef ]
• Spanaki, K.; Sivarajah, U.; Fakhimi, M.; Despoudi, S.; Irani, Z. Disruptive technologies in agricultural operations: A systematic review of AI-driven AgriTech research. Ann. Oper. Res. 2022 , 308 , 491–524. [ Google Scholar ] [ CrossRef ]
• Kamble, S.; Gunasekaran, A.; Sharma, R. Modeling the blockchain enabled traceability in agriculture supply chain. Int. J. Inf. Manag. 2020 , 52 , 101967. [ Google Scholar ] [ CrossRef ]
• Wamba, S.F.; Queiroz, M.M. Blockchain in the operations and supply chain management: Benefits, challenges and future research opportunities. Int. J. Inf. Manag. 2020 , 52 , 102064. [ Google Scholar ] [ CrossRef ]
• Moore, W.B.; Felo, A. The evolution of accounting technology education: Analytics to STEM. J. Educ. Bus. 2022 , 97 , 105–111. [ Google Scholar ] [ CrossRef ]
• Brito, C.R.; Ciampi, M.M.; Sluss, J.J.; Santos, H.D. Trends in Engineering Education: A Disruptive View for not so far Future. In Proceedings of the 18th International Conference on Information Technology Based Higher Education and Training (ITHET), Magdeburg, Germany, 26–27 September 2019. [ Google Scholar ]
• Ghani, A. Engineering education at the age of Industry 5.0—Higher education at the crossroads. World Trans. Eng. Technol. Educ. 2022 , 20 , 112–117. [ Google Scholar ]
• Bühler, M.M.; Jelinek, T.; Nübel, K. Training and Preparing Tomorrow’s Workforce for the Fourth Industrial Revolution. Educ. Sci. 2022 , 12 , 782. [ Google Scholar ] [ CrossRef ]
• Chaka, C. Is Education 4.0 a Sufficient Innovative, and Disruptive Educational Trend to Promote Sustainable Open Education for Higher Education Institutions? A Review of Literature Trends. Front. Educ. 2022 , 7 , 226. [ Google Scholar ] [ CrossRef ]
• Choi, T.-M.; Kumar, S.; Yue, X.; Chan, H.-L. Disruptive Technologies and Operations Management in the Industry 4.0 Era and Beyond. Prod. Oper. Manag. 2022 , 31 , 9–31. [ Google Scholar ] [ CrossRef ]
• Bengoechea, J.; Bell, A. The Impact of 21st Century Technology in Higher Education: The Role of Artificial Intelligence. Int. J. Educ. Pedagog. Sci. 2022 , 16 , 493–496. [ Google Scholar ]
• Miao, F.; Wayne, H.; Ronghuai, H.; Hui, Z. AI and Education: A Guidance for Policymakers ; UNESCO Publishing: Paris, France, 2021. [ Google Scholar ]
• Pornpongtechavanich, P.; Eambunnapong, K.; Daengsi, T.; Nilsook, P. Critical success factors for smart-professional disruptor in university. Int. J. Eval. Res. Educ. 2022 , 11 , 1696–1703. [ Google Scholar ] [ CrossRef ]
• Molenaar, I. Towards hybrid human-AI learning technologies. Eur. J. Educ. 2022 , 57 , 632–645. [ Google Scholar ] [ CrossRef ]
• Holmes, W.; Tuomi, I. State of the art and practice in AI in education. Eur. J. Educ. 2022 , 53 , 542–570. [ Google Scholar ] [ CrossRef ]
• Zeeshan, K.; Hämäläinen, T.; Neittaanmäki, P. Internet of Things for Sustainable Smart Education: An Overview. Sustainability 2022 , 14 , 4293. [ Google Scholar ] [ CrossRef ]
• Ciolacu, M.; Svasta, P.M.; Berg, W.; Popp, H.; IEEE. Education 4.0 for Tall Thin Engineer in a Data Driven Society. In Proceedings of the 23rd IEEE International Symposium for Design and Technology in Electronic Packaging (SIITME), Constanta, Romania, 26–29 October 2022; pp. 438–443. [ Google Scholar ]
• Ahmad, T. Scenario based approach to re-imagining future of higher education which prepares students for the future of work. High. Educ. Ski. Work-Based Learn. 2019 , 10 , 217–238. [ Google Scholar ] [ CrossRef ]
• Yang, K.; Shi, Y.M.; Zhou, Y.; Yang, Z.P.; Fu, L.Q.; Chen, W. Federated Machine Learning for Intelligent IoT via Reconfigurable Intelligent Surface. IEEE Netw. 2020 , 34 , 16–22. [ Google Scholar ] [ CrossRef ]
• Kasinathan, P.; Pugazhendhi, R.; Elavarasan, R.M.; Ramachandaramurthy, V.K.; Ramanathan, V.; Subramanian, S.; Kumar, S.; Nandhagopal, K.; Raghavan, R.R.V.; Rangasamy, S.; et al. Realization of Sustainable Development Goals with Disruptive Technologies by Integrating Industry 5.0, Society 5.0, Smart Cities and Villages. Sustainability 2022 , 14 , 15258. [ Google Scholar ] [ CrossRef ]
• Sgantzos, K.; Grigg, I. Artificial Intelligence Implementations on the Blockchain. Use Cases and Future Applications. Future Internet 2019 , 11 , 170. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Corchado, J.M.; Trabelsi, S. Advances in Sustainable Smart Cities and Territories. Electronics 2022 , 11 , 1280. [ Google Scholar ] [ CrossRef ]
• Xu, Y. Programmatic Dreams: Technographic Inquiry into Censorship of Chinese Chatbots. Soc. Media + Soc. 2018 , 4 , 2056305118808780. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Zweispace. Zweispace Won the Best Startup Award for Real Estate and Construction Batch at the Plug and Play Summer Summit 2020. Available online: https://en.zweispace.co.jp/2020/08/04/zweispace-won-the-best-startup-award-for-real-estate-and-construction-batch-at-the-plug-and-play-summer-summit-2020/ (accessed on 4 August 2022).
• Ortega-Fernández, A.; Martín-Rojas, R.; García-Morales, V. Artificial Intelligence in the Urban Environment: Smart Cities as Models for Developing Innovation and Sustainability. Sustainability 2020 , 12 , 7860. [ Google Scholar ] [ CrossRef ]
• Schintler, L.A.; McNeely, C.L. Artificial intelligence, institutions, and resilience: Prospects and provocations for cities. J. Urban Manag. 2022 , 11 , 256–268. [ Google Scholar ] [ CrossRef ]
• Fu, G.; Jin, Y.; Sun, S.; Yuan, Z.; Butler, D. The role of deep learning in urban water management: A critical review. Water Res. 2022 , 223 , 118973. [ Google Scholar ] [ CrossRef ]
• Ullah, F. Smart Tech 4.0 in the Built Environment: Applications of Disruptive Digital Technologies in Smart Cities, Construction, and Real Estate. Buildings 2022 , 12 , 1516. [ Google Scholar ] [ CrossRef ]
• Ullah, F.; Sepasgozar, S.M.E.; Wang, C.X. A Systematic Review of Smart Real Estate Technology: Drivers of, and Barriers to, the Use of Digital Disruptive Technologies and Online Platforms. Sustainability 2018 , 10 , 3142. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Ghobakhloo, M. Industry 4.0, digitization, and opportunities for sustainability. J. Clean. Prod. 2020 , 252 , 119869. [ Google Scholar ] [ CrossRef ]
• Khanna, A.; Sah, A.; Bolshev, V.; Jasinski, M.; Vinogradov, A.; Leonowicz, Z.; Jasiński, M. Blockchain: Future of e-Governance in Smart Cities. Sustainability 2021 , 13 , 11840. [ Google Scholar ] [ CrossRef ]
• McLean, J.; Mackenzie, R. Digital justice in Australian visa application processes? Altern. Law J. 2019 , 44 , 291–296. [ Google Scholar ] [ CrossRef ]
• Ishengoma, F.R.; Shao, D.; Alexopoulos, C.; Saxena, S.; Nikiforova, A. Integration of artificial intelligence of things (AIoT) in the public sector: Drivers, barriers and future research agenda. Digit. Policy Regul. Gov. 2022 , 24 , 449–462. [ Google Scholar ] [ CrossRef ]
• Rapanyane, M.B.; Sethole, F.R. The rise of artificial intelligence and robots in the 4th Industrial Revolution: Implications for future South African job creation. Contemp. Soc. Sci. 2020 , 15 , 489–501. [ Google Scholar ] [ CrossRef ]
• Mesko, B. The role of artificial intelligence in precision medicine. Expert Rev. Precis. Med. Drug Dev. 2017 , 2 , 239–241. [ Google Scholar ] [ CrossRef ]
• Brougham, D.; Haar, J. Smart Technology, Artificial Intelligence, Robotics, and Algorithms (STARA): Employees’ perceptions of our future workplace. J. Manag. Organ. 2018 , 24 , 239–257. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Frey, C.B.; Osborne, M.A. The future of employment: How susceptible are jobs to computerisation? Technol. Forecast. Soc. Chang. 2017 , 114 , 254–280. [ Google Scholar ] [ CrossRef ]

Click here to enlarge figure

Share and Cite

Păvăloaia, V.-D.; Necula, S.-C. Artificial Intelligence as a Disruptive Technology—A Systematic Literature Review. Electronics 2023 , 12 , 1102. https://doi.org/10.3390/electronics12051102

Păvăloaia V-D, Necula S-C. Artificial Intelligence as a Disruptive Technology—A Systematic Literature Review. Electronics . 2023; 12(5):1102. https://doi.org/10.3390/electronics12051102

Păvăloaia, Vasile-Daniel, and Sabina-Cristiana Necula. 2023. "Artificial Intelligence as a Disruptive Technology—A Systematic Literature Review" Electronics 12, no. 5: 1102. https://doi.org/10.3390/electronics12051102

Article Metrics

Article access statistics, further information, mdpi initiatives, follow mdpi.

Subscribe to receive issue release notifications and newsletters from MDPI journals

Grab your spot at the free arXiv Accessibility Forum

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:.

• 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 .

Educational resources and simple solutions for your research journey

Top AI Tools for Literature Review 

As researchers, one of the most important steps in conducting a comprehensive study is to perform a literature review. Some of the common challenges researchers face include the overwhelming volume of literature, difficulty in identifying relevant studies, synthesizing findings, and keeping up with the latest research. Fortunately, AI tools for literature reviews are helping researchers overcome these challenges by providing efficient and effective ways to search, filter, and analyze literature.   

In this blog post, we’ll explore some of the top AI tools for literature review and how they can help streamline the research process.   

Table of Contents

Top five AI tools for literature review  

Conducting literature review is a long and arduous task where researchers have to closely go through vast information sources. However, with these five AI literature review tools, sifting large volumes of information easy.   

R Discovery  

R Discovery is one of the largest scholarly content repositories allowing you access to 250M+ research papers. R Discovery accelerates your research discovery journey, with latest and relevant content in your area of interest. Below are a few benefits of R Discovery tailored to students and researchers to enhance their research finding and reading experience:   

• Personalized Research Reading Feeds – R Discovery curates an academic reading library based on the user’s interests. It provides personalized reading recommendations with daily alerts on top papers, ensuring that users are always updated with the latest and most relevant research in their fields.
• Multiple reading lists – You can create and manage separate reading lists for different literature reviews you’re conducting, keeping your research organized.
• Multilingual & Full-Text Audio Features – R Discovery offers audio versions of research abstracts or full-text articles in more than 30+ languages. This feature is particularly beneficial for non-native English speakers, allowing them to listen to or read research papers in their preferred language, thus enhancing accessibility and comprehension  
• Smart Research Alerts – The app sends targeted research alerts and notifications to users based on their reading habits and preferences. Users receive no more than three research paper notifications per day to avoid information overload. The notifications include curated lists of top research papers, updates from preferred journals, and alerts on full-text articles available for reading.   
• Integration with Reference Managers – The platform offers auto-sync capabilities with reference managers like Zotero and Mendeley, ensuring that users’ libraries are up to date with the papers they save or remove  

Mendeley is a comprehensive reference management software that serves as an essential tool for researchers, academics, and students engaged in literature review and research management. Founded in 2007 by PhD students and acquired by Elsevier in 2013, Mendeley has evolved into a multifaceted platform that facilitates the organization, sharing, and discovery of research papers.      

Below are the detailed features of this AI tool for literature reviews:  

• Reference Management – Mendeley allows users to store, organize, and search all their references from a single library. This feature simplifies the process of managing a vast amount of literature, making it easier to access and cite these references in future research.
• Viewing and Annotation – Users can open PDFs directly within Mendeley’s PDF viewer, where they can add highlights and notes to the document. These annotations are stored in the user’s Mendeley account, and a new PDF file containing all annotations can be exported, facilitating collaborative review and personal notetaking.
• Collaboration and Sharing – Mendeley supports collaboration through the creation of private groups, allowing users to share references and annotated documents with co-workers or research team members. This feature enhances the collaborative aspect of literature review by enabling shared access to key resources.
• Literature Search and Discovery – While a dedicated literature search feature was removed from the latest version of Mendeley, the platform still offers capabilities for discovering relevant research. Users can import references from other sources and utilize Mendeley’s academic social network to find and share literature.
• Citation and Bibliography Generation – Mendeley simplifies the citation process with Mendeley Cite, an add-in for Microsoft Word that automates the generation of citations and bibliographies in various citation styles. This feature significantly reduces the time and effort required to accurately cite sources during a literature review.  

Zotero is an open-access, easy-to-use reference management tool designed to assist with the collection, organization, citation, and sharing of research sources. It serves as a personal research assistant for students, researchers, and academics, helping them manage their literature review process efficiently.    

• Reference Management – Zotero allows users to collect citations from various sources, including books, articles, media, webpages, and more. It provides a centralized library where users can organize these references into collections, tag them with keywords, and create saved searches that automatically populate with relevant materials.   
• PDF Viewing and Annotation – Zotero has a built-in PDF viewer that enables users to highlight text, add sticky notes, and take snapshots of images or charts within PDFs. Annotations made in the PDF viewer are saved within Zotero and can be extracted as notes, making them fully searchable and easier to organize.  
• Collaboration and Sharing – Zotero’s Groups feature allows users to collaborate with other Zotero users through shared libraries. Users can create private, public closed, or public open groups to work on collaborative research projects, distribute course materials, or build collaborative bibliographies  
• Citation and Bibliography Generation – Zotero integrates with word processors like Microsoft Word, LibreOffice, and Google Docs to insert citations and bibliographies directly into documents. It supports over 10,000 citation styles, allowing users to format their work to match any style guide or publication  

Scholarcy  

Scholarcy is an innovative tool designed to assist researchers, students, and academics in managing the often-overwhelming task of conducting literature reviews. It leverages artificial intelligence to automate the extraction of key information from academic papers, creating structured summaries that make it easier to evaluate and understand research articles. Below are the detailed features of Scholarcy that are particularly useful for conducting literature reviews:    

• Flashcard Summaries – Scholarcy generates interactive summary flashcards from research papers, book chapters, and other documents. These flashcards highlight key information, providing a compact and easy-to-read overview of the text. This feature is perfect for skim reading or getting to the key points of an article before reading it in full.   
• Smart Highlighting and Analysis – The tool guides users to important sections of text and helps interpret them through smart highlighting and analysis. Scholarcy identifies factual statements and findings, highlighting them in different colors (blue for factual statements and orange for findings) to facilitate quick understanding of the content.   
• Access to Full Text and Cited Papers – Scholarcy provides convenient access to the full text of articles and cited papers. It uses icons to link directly to the full text and to services like Libkey, which provides access via institutional subscriptions. Additionally, clicking on the Scholarcy icon shows the key findings from cited articles, offering a quick overview of the citation context.
• Literature Discovery and Screening – Scholarcy aids in the discovery and screening of new literature. It can source, screen, and store academic literature more efficiently than traditional methods. The Scholarcy browser extension provides a detailed Synopsis and Highlights for a more comprehensive screening than what an abstract alone can offer. This process can take as little as five minutes, allowing readers to absorb the underlying points of the literature quickly  
• Reference Management Integration – Scholarcy allows for the export of flashcards to reference management software like Zotero. This integration enables users to see not only the reference of the article in their Zotero library but also the key highlights and structured summaries generated by Scholarcy.   

Unpaywall  

Offering open access to scholarly articles, Unpaywall is a free database built from over 50,000 publishers and repositories globally.  They also leverage open data sources like PubMed Central, DOAJ, Crossref, and DataCite. Major databases including Dimensions, Scopus, and Web of Science have incorporated Unpaywall. For users with Digital Object Identifiers (DOIs), Unpaywall provides various tools to find open access and full-text articles. Data access is available through REST API, R API Wrapper, the Simple Query Tool, or by downloading the entire dataset. Below are the features of this AI tool for literature review  

• Simple Query – The Simple Query Tool offered by Unpaywall helps users to determine if there is an open access (OA) version of a list of articles they are interested in. It is particularly useful for users with a list of Digital Object Identifiers (DOIs) for articles and are seeking free, full-text versions of these articles are available through Unpaywall’s extensive database.
• Browser Extension – The Unpaywall browser extension automatically searches for legally available, free versions of scholarly articles as you browse. When you come across a research article online, the extension checks Unpaywall’s database for an open access version. If such a version is available, a green tab appears on the side of your browser, which you can click to access the full text of the article directly. This feature is powered by an index of over 20 million free, legal full-text PDFs, making it a powerful ally in the quest for open access literature.  

There are many AI tools for literature review available for your assistance. However, the best tool for you depends on your specific needs. Do you prioritize comprehensive search and full-text access? Easy organization and citation management? Or perhaps AI-powered summaries to grasp key findings quickly?  

Evaluate the functionalities of each tool and choose the one that best complements your research workflow. With the right AI tool, your literature review can become a breeze.   

R Discovery is a literature search and research reading platform that accelerates your research discovery journey by keeping you updated on the latest, most relevant scholarly content. With 250M+ research articles sourced from trusted aggregators like CrossRef, Unpaywall, PubMed, PubMed Central, Open Alex and top publishing houses like Springer Nature, JAMA, IOP, Taylor & Francis, NEJM, BMJ, Karger, SAGE, Emerald Publishing and more, R Discovery puts a world of research at your fingertips.  

Try R Discovery Prime FREE for 1 week or upgrade at just US$72 a year to access premium features that let you listen to research on the go, read in your language, collaborate with peers, auto sync with reference managers, and much more. Choose a simpler, smarter way to find and read research – Download the app and start your free 7-day trial today !  

Related Posts

Top 7 Tried and Tested Paraphrasing Techniques

Annex vs Appendix: What is the difference?

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

What to read next: books on AI

July 28, 2024 Literature on artificial intelligence (AI) is everywhere, and for good reason. McKinsey research  estimates that generative AI could add between $2.6 trillion to $4.4 trillion annually to the economy while increasing the impact of all AI by 15 to 40 percent. No matter how much you already know, there's always more to learn about the quickly evolving technology. Here are six books recommended by leaders, including McKinsey’s Yuval Atsmon and Lareina Yee . For more suggestions from 50-plus global executives, editors in chief, and McKinsey leaders, check out “ What to read next: McKinsey’s 2024 annual book recommendations .”

AI Needs You: How We Can Change AI’s Future and Save Our Own  by Verity Harding Recommended by: Lila Ibrahim , COO, Google DeepMind; Young Global Leader, World Economic Forum

The Singularity Is Nearer: When We Merge with AI  by Ray Kurzweil Recommended by: Yuval Atsmon , senior partner, McKinsey

Co-intelligence: Living and Working with AI  by Ethan Mollick Recommended by: Lareina Yee , senior partner, McKinsey Reid Hoffman , cofounder, LinkedIn; partner, Greylock Partners

God, Human, Animal, Machine: Technology, Metaphor, and the Search for Meaning  by Meghan O’Gieblyn  Recommended by: Nicholas Dirks , CEO and president, New York Academy of Sciences; former chancellor, University of California, Berkeley

Ideas That Created the Future: Classic Papers of Computer Science  by Harry R. Lewis  Recommended by: Amy Webb , founder and CEO, Future Today Institute

The Coming Wave: Technology, Power, and the Twenty-First Century’s Greatest Dilemma  by Mustafa Suleyman, with Michael Bhaskar  Recommended by: Lareina Yee , senior partner, McKinsey 

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, common questions. great answers., how do researchers use elicit.

Over 2 million researchers have used Elicit. 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 in theoretical or non-empirical domains.

What types of data can Elicit search over?

Elicit searches across 125 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.

How can you get in contact with the team?

You can email us at [email protected] or post in our Slack community ! We log and incorporate all user comments, and will do our best to reply to every inquiry 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..

MIT Technology Review

• Newsletters

Google’s new weather prediction system combines AI with traditional physics

Weather and climate experts are divided on whether AI or more traditional methods are most effective. In this new model, Google’s researchers bet on both.

• James O'Donnell archive page

Researchers from Google have built a new weather prediction model that combines machine learning with more conventional techniques, potentially yielding accurate forecasts at a fraction of the current cost. 

The model, called NeuralGCM and described in a paper in Nature today, bridges a divide that’s grown among weather prediction experts in the last several years. 

While new machine-learning techniques that predict weather by learning from years of past data are extremely fast and efficient, they can struggle with long-term predictions. General circulation models, on the other hand, which have dominated weather prediction for the last 50 years, use complex equations to model changes in the atmosphere and give accurate projections, but they are exceedingly slow and expensive to run. Experts are divided on which tool will be most reliable going forward. But the new model from Google instead attempts to combine the two. 

“It’s not sort of physics versus AI. It’s really physics and AI together,” says Stephan Hoyer, an AI researcher at Google Research and a coauthor of the paper. 

The system still uses a conventional model to work out some of the large atmospheric changes required to make a prediction. It then incorporates AI, which tends to do well where those larger models fall flat—typically for predictions on scales smaller than about 25 kilometers, like those dealing with cloud formations or regional microclimates (San Francisco’s fog, for example). “That’s where we inject AI very selectively to correct the errors that accumulate on small scales,” Hoyer says.

The result, the researchers say, is a model that can produce quality predictions faster with less computational power. They say NeuralGCM is as accurate as one-to-15-day forecasts from the European Centre for Medium-Range Weather Forecasts (ECMWF), which is a partner organization in the research. 

But the real promise of technology like this is not in better weather predictions for your local area, says Aaron Hill, an assistant professor at the School of Meteorology at the University of Oklahoma, who was not involved in this research. Instead, it’s in larger-scale climate events that are prohibitively expensive to model with conventional techniques. The possibilities could range from predicting tropical cyclones with more notice to modeling more complex climate changes that are years away. 

“It’s so computationally intensive to simulate the globe over and over again or for long periods of time,” Hill says. That means the best climate models are hamstrung by the high costs of computing power, which presents a real bottleneck to research. 

AI-based models are indeed more compact. Once trained, typically on 40 years of historical weather data from ECMWF, a machine-learning model like Google’s GraphCast can run on less than 5,500 lines of code, compared with the nearly 377,000 lines required for the model from the National Oceanic and Atmospheric Administration, according to the paper. 

NeuralGCM, according to Hill, seems to make a strong case that AI can be brought in for particular elements of weather modeling to make things faster, while still keeping the strengths of conventional systems.

“We don't have to throw away all the knowledge that we’ve gained over the last 100 years about how the atmosphere works,” he says. “We can actually integrate that with the power of AI and machine learning as well.”

Hoyer says using the model to predict short-term weather has been useful for validating its predictions, but that the goal is indeed to be able to use it for longer-term modeling, particularly for extreme weather risk. 

NeuralGCM will be open source. While Hoyer says he looks forward to having climate scientists use it in their research, the model may also be of interest to more than just academics. Commodities traders and agricultural planners pay top dollar for high-resolution predictions, and the models used by insurance companies for products like flood or extreme weather insurance are struggling to account for the impact of climate change. 

While many of the AI skeptics in weather forecasting have been won over by recent developments, according to Hill, the fast pace is hard for the research community to keep up with. “It’s gangbusters,” he says—it seems as if a new model is released by Google, Nvidia, or Huawei every two months. That makes it difficult for researchers to actually sort out which of the new tools will be most useful and apply for research grants accordingly. 

“The appetite is there [for AI],” Hill says. “But I think a lot of us still are waiting to see what happens.”

Artificial intelligence

What is ai.

Everyone thinks they know but no one can agree. And that’s a problem.

• Will Douglas Heaven archive page

What are AI agents? 

The next big thing is AI tools that can do more complex tasks. Here’s how they will work.

• Melissa Heikkilä archive page

How to use AI to plan your next vacation

AI tools can be useful for everything from booking flights to translating menus.

• Rhiannon Williams archive page

Why Google’s AI Overviews gets things wrong

Google’s new AI search feature is a mess. So why is it telling us to eat rocks and gluey pizza, and can it be fixed?

Stay connected

Get the latest updates from mit technology review.

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at [email protected] with a list of newsletters you’d like to receive.

AI Literature Review Generator

Generate high-quality literature reviews fast with ai.

• 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 speech generator, detailed lesson plan builder, love letter generator.

• SUGGESTED TOPICS
• The Magazine
• Newsletters
• Managing Yourself
• Managing Teams
• Work-life Balance
• The Big Idea
• Data & Visuals
• Reading Lists
• Case Selections
• HBR Learning
• Topic Feeds
• Account Settings
• Email Preferences

The Uneven Distribution of AI’s Environmental Impacts

• Shaolei Ren
• Adam Wierman

How companies can responsibly manage the growing water and energy demands of their data centers across the world.

The training process for a single AI model, such as an LLM, can consume thousands of megawatt hours of electricity and emit hundreds of tons of carbon. AI model training can also lead to the evaporation of an astonishing amount of freshwater into the atmosphere for data center heat rejection, potentially exacerbating stress on our already limited freshwater resources. These environmental impacts are expected to escalate considerably, and there remains a widening disparity in how different regions and communities are affected. The ability to flexibly deploy and manage AI computing across a network of geographically distributed data centers offers substantial opportunities to tackle AI’s environmental inequality by prioritizing disadvantaged regions and equitably distributing the overall negative environmental impact.

The adoption of artificial intelligence has been rapidly accelerating across all parts of society, bringing the potential to address shared global challenges such as climate change and drought mitigation. Yet underlying the excitement surrounding AI’s transformative potential are increasingly large and energy-intensive deep neural networks. And the growing demands of these complex models are raising concerns about AI’s environmental impact.

• Shaolei Ren is an associate professor of electrical and computer engineering at the University of California, Riverside. He has taught and researched computational sustainability for more than a decade. His work on sustainable AI has been featured in many international AI governance and ethics guidelines, contributed to K-12 education materials, led to industry innovations like real-time water footprint reporting tools, and gained worldwide media coverage.
• Adam Wierman is the Carl F. Braun Professor in the Department of Computing and Mathematical Sciences at Caltech. His research strives to make the networked systems that govern our world sustainable and resilient. He is best known for his work spearheading the design of algorithms for sustainable data centers, which has seen significant industry adoption, as well as his work on heavy tails, including his coauthored book, The Fundamentals of Heavy Tails .

Partner Center

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

“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

As a full-time researcher, Litmaps has become an indispensable tool in my arsenal. The Seed Maps and Discover features of Litmaps have transformed my literature review process, streamlining the identification of key citations while revealing previously overlooked relevant literature, ensuring no crucial connection goes unnoticed. A true game-changer indeed!

Ritwik Pandey

Doctoral Research Scholar – Sri Sathya Sai Institute of Higher Learning

Using Litmaps for my research papers has significantly improved my workflow. Typically, I start with a single paper related to my topic. Whenever I find an interesting work, I add it to my search. From there, I can quickly cover my entire Related Work section.

David Fischer

Research Associate – University of Applied Sciences Kempten

“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

“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

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

Professor at The Chinese University of Hong Kong

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

Katholieke Universiteit Leuven, Belgium

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

KU Leuven, Belgium

“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

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

Swansea University, Wales

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

Ali Mohammed-Djafari

Director of Research at LSS-CNRS, France

“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

As a person who is an early researcher and identifies as dyslexic, I can say that having research articles laid out in the date vs cite graph format is much more approachable than looking at a standard database interface. I feel that the maps Litmaps offers lower the barrier of entry for researchers by giving them the connections between articles spaced out visually. This helps me orientate where a paper is in the history of a field. Thus, new researchers can look at one of Litmap's "seed maps" and have the same information as hours of digging through a database.

Baylor Fain

Postdoctoral Associate – University of Florida

We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.

• 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 1 billion 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 500,000 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 currently enrolled students with valid student ID.

per month, billed quarterly

For a team that wants professional licenses for all members.

per month, per user, 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

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.

• 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

A Guide to Using AI Tools to Summarize Literature Reviews

Table of Contents

Needless to say, millions of scientific articles are getting published every year making it difficult for a researcher to read and comprehend all the relevant publications.

Back then, researchers used to manually conduct literature reviews by sifting through hundreds of research papers to get the significant information required for the research.

Fast forward to 2023 — things have turned out quite distinct and favorable. With the inception of AI tools, the literature review process is streamlined and researchers can summarize hundreds of research articles in mere moments. They can save time and effort by using AI tools to summarize literature reviews.

This article articulates the role of the top AI tools used to summarize literature reviews. You can also learn how AI is used as a powerful tool for summarizing scientific articles and understanding the impact of AI on academic research.

Understanding the Role of AI Tools in Literature Reviews

Before we talk about the benefits of AI tools to summarize literature reviews, let’s understand the concept of AI and how it streamlines the literature review process.

Artificial intelligence tools are trained on large language models and they are programmed to mimic human tasks like problem-solving, making decisions, understanding patterns, and more. When Artificial Intelligence and machine learning algorithms are implemented in literature reviews, they help in processing vast amounts of information, identifying highly relevant studies, and generating quick and concise summaries — TL;DR summaries.

AI has revolutionized the process of literature review by assisting researchers with powerful AI-based tools to read, analyze, compare, contrast, and extract relevant information from research articles.

By using natural language processing algorithms, AI tools can effectively identify key concepts, main arguments, and relevant findings from multiple research articles at once. This assists researchers in quickly understanding the overview of the existing literature on a respective topic, saving their valuable time and effort.

Key Benefits of Using AI Tools to Summarize Literature Review

1. best alternative to traditional literature review.

Traditional literature reviews or manual literature reviews can be incredibly time-consuming and often require weeks or even months to complete. Researchers have to sift through myriad articles manually, read them in detail, and highlight or extract relevant information. This process can be overwhelming, especially when dealing with a large number of studies.

However, with the help of AI tools, researchers can greatly save time and effort required to discover, analyze, and summarize relevant studies. AI tools with their NLP and machine learning algorithms can quickly analyze multiple research articles and generate succinct summaries. This not only improves efficiency but also allows researchers to focus on the core analysis and interpretation of the compiled insights.

2. AI tools aid in swift research discovery!

AI tools also help researchers save time in the discovery phase of literature reviews. These AI-powered tools use semantic search analysis to identify relevant studies that might go unnoticed in traditional literature review methods. Also, AI tools can analyze keywords, citations , and other metadata to prompt or suggest pertinent articles that align and correlate well with the researcher’s search query.

3. AI Tools ensure to stay up to date with the most research ideas!

Another advantage of using AI-powered tools in literature reviews is their ability to handle the ever-increasing volume of published scientific research. With the exponential growth of scientific literature, it has become increasingly challenging for researchers to keep up with the latest scientific research and biomedical innovations.

However, AI tools can automatically scan and discover new publications, ensuring that researchers stay up-to-date with the most recent developments in their field of study.

4. Improves efficiency and accuracy of Literature Reviews

The use of AI tools in literature review reduces the occurrences of human errors that may occur during traditional literature review or manual document summarization. So, literature review AI tools improve the overall efficiency and accuracy of literature reviews, ensuring that researchers can access relevant information promptly by minimizing human errors.

List of AI Tools to Streamline Literature Reviews

We have several AI-powered tools to summarize literature reviews. They utilize advanced algorithms and natural language processing techniques to analyze and summarize lengthy scientific articles.

Let's take a look at some of the most popular AI tools to summarize literature reviews.

SciSpace Literature Review

Semantic scholar, paper digest.

SciSpace Literature Review is the best AI tool for summarizing literature review. It is the go-to tool that summarizes articles in seconds. It uses natural language processing models GPT 3.5 and GPT 4.0 to generate concise summaries. It is an effective and efficient AI-powered tool to streamline the literature review process and summarize multiple research articles at once. Once you enter a keyword, research topic, or question, it initiates your literature review process by providing instant insights from the top 5 highly relevant papers at the top.

These insights are backed by citations that allow you to refer to the source. All the resultant relevant papers appear in an easy-to-digest tabular format explaining each of the sections used in the paper in different columns. You can also customize the table by adding or removing the columns according to your research needs. This is the unique feature of this literature review AI tool.

SciSpace Literature review stands out as the best AI tool to summarize literature review by providing concise TL;DR text and summaries for all the sections used in the research paper. This way, it makes the review process easier for any researcher, and could comprehend more research papers in less time.

Try SciSpace Literature Review now!

Semantic Scholar is an AI-powered search engine that helps researchers find relevant research papers based on the keyword or research topic. It works similar to Google Scholar.It helps you discover and understand scientific research by providing suitable research papers. The database has over 200 million research articles, you can filter out the results based on the field of study, author, date of publication, and journals or conferences.

They have recently released the Semantic Reader — an AI-powered tool for scientific readers that enhances the reading process. This is available in the beta version.

Try Semantic Scholar here

Paper Digest — another valuable text summarizer tool (AI-powered tool) that summarizes the literature review and helps you get to the core insights of the research paper in a few minutes! This powerful tool works pretty straightforwardly and generates summaries of research papers. You just need to input the article URL or DOI and click on “Digest” to get the summaries. It comes for free and is currently in the beta version.

You can access Paper Digest here !

SciSummary is another AI tool that summarizes scientific articles and literature review. It uses natural language processing algorithm to generate concise summaries. You need to upload the document on the dashboard or send the article link via email and your summaries will be generated and delivered to your inbox. This is the best AI-powered tool that helps you read and understand lengthy and complicated research papers. It has different pricing plans (both free and premium) which start at $4.99/month, you can choose the plans according to your needs.

You can access SciSummary here

Step-by-Step Guide to Using AI Tools to Summarize Literature Reviews

Here’s a short step-by-step guide that clearly articulates how to use AI tools for summary generation!

• Select the AI-powered tool that best suits your research needs.
• Once you've chosen a tool, you must provide input, such as an article link, DOI, or PDF, to the tool.
• The AI tool will then process the input using its algorithms and techniques, generating a summary of the literature.
• The generated summary will contain the most important information, including key points, methodologies, and conclusions in a succinct format.
• Review and assess the generated summaries to ensure accuracy and relevance.

Challenges of using AI tools for summarization

AI tools are designed to generate precise summaries, however, they may sometimes miss out on important facts or misinterpret specific information.

Here are the potential challenges and risks researchers should be wary of when using AI tools to summarize literature reviews!

1. Lack of contextual intelligence

AI-powered tools cannot ensure that they completely understand the context of the research papers. This leads to inappropriate or misleading summaries of similar academic papers.

To combat this, researchers should feed additional context to the AI prompt or use AI tools with more advanced training models that can better understand the complexities of the research papers.

2. AI tools cannot ensure foolproof summaries

While AI tools can immensely speed up the summarization process, but, they may not be able to capture the complete essence of a research paper or accurately decrypt complex concepts.

Therefore, AI tools are just to be considered as technology aids rather than replacements for human analysis or understanding of key information.

3. Potential bias in the generated summaries

AI-powered tools are largely trained on the existing data, and if the training data is biased, it can eventually lead to biased summaries.

Researchers should be cautious and ensure that the training data is diverse and representative of various sources, different perspectives, and research domains.

4. Quality of the input article affects the summary output

The quality of the research article that we upload or input data also has a direct effect on the accuracy of the generated summaries.

If the input article is poorly written or contains errors, the AI tool might not be able to generate coherent and accurate summaries. Researchers should select high-quality academic papers and articles to obtain reliable and informative summaries.

Concluding!

AI summarization tools have a substantial impact on academic research. By leveraging AI tools, researchers can streamline the literature review process, enabling them to stay up-to-date with the latest advancements in their field of study and make informed decisions based on a comprehensive understanding of current knowledge.

By understanding the role of AI tool to summarize literature review, exploring different AI tools for summarization, following a systematic review process, and assessing the impact of these tools on their academic research, researchers can harness AI tools in enhancing their literature review processes.

If you are also keen to explore the best AI-powered tool for summarizing the literature review process, head over to SciSpace Literature Review and start analyzing the research papers right away — SciSpace Literature Review

Frequently Asked Questions

Give an overview of the main points from each paper and integrate them into a coherent whole, by outlining the importance, limitations, and unique insights from the reviewed literature.

SciSpace Literature Review is the best AI tool for summarizing research articles. It can summarize articles in seconds and provide detailed and focused insights.

Some of the best AI tools for summarizing literature reviews includes: SciSpace, Semantic Scholar, Paper Digest, and SciSummary.

For a Ph.D.dissertation, a literature review summary typically comprises a chapter (around 8000 words), while for a Master’s thesis, it is usually around 2000 - 3000 words.

Few More Insightful Articles — Just for you!

10 best ai for essay writing, role of ai in systematic literature review, how to use ai tools for conducting a literature review, research paper summarizer | an overview of the best ai summarizers, you might also like.

Boosting Citations: A Comparative Analysis of Graphical Abstract vs. Video Abstract

The Impact of Visual Abstracts on Boosting Citations

Introducing SciSpace’s Citation Booster To Increase Research Visibility

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!