medigraphic.com
ISSN 2007-5057 (Print)
Investigación en Educación Médica

2023, Number 47

<< Back Next >>

Inv Ed Med 2023; 12 (47)

Towards enhanced literature review efficiency powered by artificial intelligence

Carbajal-Degante E, Hernández Gutiérrez M, Sánchez-Mendiola M

Language: Spanish
References: 29
Page: 111-119
PDF size: 589.76 Kb.


ABSTRACT

Literature reviews for research and teaching tasks is increasingly facing new challenges, mainly due to the considerable growth of bibliographic material in all disciplines. Primarily, the search and selection of information become exhausting and overwhelming due to the lack of planning in the systematic collection of documents, as well as the improper handling of metadata and the high variability of the results offered by automatic search mechanisms. In this sense, artificial intelligence is transforming the landscape of literature review by employing systems capable of quickly analyzing and interpreting the content of text documents while providing very accurate results, higher than traditional search engines. This paper aims to describe recent advances in the intelligent integration process of literature review methods, referring to the use of machine and deep learning techniques associated with optimization stages of natural language processing. Finally, we address the implications of employing systems capable of making judgments and making decisions regarding the usefulness and relevance of the analyzed data.


REFERENCES

  1. Ibáñez A. 2022: Más tráfico en Internet que el acumulado entres décadas. [Online]. 2019 [citado 2023 Mayo 6]. Disponibleen: https://blog.sarenet.es/trafico-web/.

  2. Extance A. How AI technology can tame the scientific literature.Nature. 2018 Septiembre;561:273-274.

  3. Majchrzak A, Markus ML, Wareham J. Designing for DigitalTransformation: Lessons for Information Systems Researchfrom the Study of ICT and Societal Challenges. MIS Quarterly.2016 Junio;40(2):267-277.

  4. Castro D, Rodríguez-Gómez D, Gairín J. Exclusion Factorsin Latin American Higher Education. Education and UrbanSociety. 2016 Julio; 49(2): p. 229-247.

  5. Zhang K, Aslan AB. AI technologies for education: Recentresearch and future directions. Computers and Education:Artificial Intelligence. 2021;2:100025.

  6. Zawacki-Richter O, Marín VI, Bond M, Gouverneur F. Systematicreview of research on artificial intelligence applicationsin higher education - where are the educators? InternationalJournal of Educational Technology in Higher Education.2019 Octubre;16(39).

  7. Salas-Pilco SZ, Yang Y. Artificial intelligence applicationsin Latin American higher education: a systematic review.International Journal of Educational Technology in HigherEducation. 2022 Abril;19(21).

  8. van de Schoot R, de Bruin J, Schram R, Zahedi P, de BoerJ, Weijdema F, et al. An open source machine learning frameworkfor efficient and transparent systematic reviews.Nature Machine Intelligence. 2021 Febrero;3:125-133.

  9. Wallace BC, Trikalinos TA, Lau J, Brodley C, Schmid CH.Semi-automated screening of biomedical citations for systematicreviews. BMC Bioinformatics. 2010 Enero;11(55).

  10. Larsen KR, Hovorka DS, Dennis AR, West JD. “Understandingthe Elephant: The Discourse Approach to BoundaryIdentification and Corpus Construction for Theory ReviewArticles”. Journal of the Association for Information Systems.2019;887-927.

  11. Zhang X, Yang A, Li S, Wang Y. Machine Reading Comprehension:a Literature Review. arXiv. 2019 Junio.

  12. Wagner G, Lukyanenko R, Paré G. Artificial intelligenceand the conduct of literature reviews. Journal of InformationTechnology. 2021 Octubre;37(2):209-226.

  13. Okoli C. A Guide to Conducting a Standalone SystematicLiterature Review. Communications of the Association forInformation Systems. 2015;37.

  14. Collins C, Dennehy D, Conboy K, Mikalef P. Artificial intelligencein information systems research: A systematic literaturereview and research agenda. International Journal ofInformation Management. 2021 Octubre;60:102383.

  15. Van de Schoot R, De Bruin J. Researcher-in-the-loop forsystematic reviewing of text databases. SciNLP: NaturalLanguage Processing and Data Mining for Scientific Text.2020 Junio.

  16. Lombaers P, de Bruin J, van de Schoot R. Reproducibility andData storage Checklist for Active Learning-Aided SystematicReviews. 2023 Enero.

  17. Ouzzani M, Hammady H, Fedorowicz Z, Elmagarmid A.Rayyan—a web and mobile app for systematic reviews. SystematicReviews. 2016 Diciembre;5.

  18. Ought. Building Elicit, the AI research assistant. [Online].2022 [citado 2023 Mayo 6]. Disponible en: https://ought.org/updates/2022-03-22-elicit.

  19. Zhao WX, Zhou K, Li J, Tang T, Wang X, Hou Y, et al. ASurvey of Large Language Models. arXiv. 2023 Marzo.

  20. Alkaissi H, McFarlane SI. Artificial Hallucinations in Chat-GPT: Implications in Scientific Writing. Cureus. 2023 Febrero;15(2).

  21. OpenAI. GPT-4 Technical Report. arXiv. 2023 Marzo.

  22. Devlin J, Chang MW, Lee K, Toutanova K. BERT: Pretrainingof Deep Bidirectional Transformers for LanguageUnderstanding. arXiv. 2019.

  23. Beltagy I, Lo K, Cohan A. SciBERT: A Pretrained LanguageModel for Scientific Text. In Proceedings of the 2019 Conferenceon Empirical Methods in Natural Language Processing and the 9th International Joint Conference on NaturalLanguage Processing (EMNLP-IJCNLP); 2019; Hong Kong,China: Association for Computational Linguistics. p. 3615-3620.

  24. Nicholson JM, Mordaunt M, Lopez P, Uppala A, Rosati D,Rodrigues NP, et al. scite: A smart citation index that displaysthe context of citations and classifies their intent using deeplearning. Quantitative Science Studies. 2021;2(3):882-898.

  25. Marshall IJ, Kuiper J, Wallace BC. RobotReviewer: evaluationof a system for automatically assessing bias in clinicaltrials. Journal of the American Medical Informatics Association.2016 Enero;23(1):193-201.

  26. Boell S, Wang B. www.litbaskets.io, an IT Artifact SupportingExploratory Literature Searches for Information SystemsResearch. In 30th Australasian Conference on InformationSystems; 2019 December.

  27. Li J, Larsen K, Abbasi A. TheoryOn: A Design Framework andSystem for Unlocking Behavioral Knowledge Through OntologyLearning. MIS Quarterly. 2020 Diciembre;44:1733-1772.

  28. d’Obrenan CvdB, Galliano F, Minton J, Botev V, Wu R. Searchingfor Carriers of the Diffuse Interstellar Bands AcrossDisciplines, using Natural Language Processing. arXiv. 2022Noviembre.

  29. Jobin A, Ienca M, Vayena E. The global landscape of AI ethicsguidelines. Nature Machine Intelligence. 2019 Septiembre;1:389-399.




2020     |     www.medigraphic.com