ChatGPT Search as a tool for scholarly tasks: evolution or devolution?

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Font-Julián, Cristina I.
• dc.contributor.author Orduña-Malea, Enrique
• dc.contributor.author Codina, Lluís
• dc.date.accessioned 2024-11-28T08:47:42Z
• dc.date.available 2024-11-28T08:47:42Z
• dc.date.issued 2024
• dc.description Includes supplementary materials for the online appendix.
• dc.description.abstract ChatGPT Search was launched on October 31 by OpenAI as a new AI-powered search engine. Among its features, it stands out for its ability to retrieve information from various online sources, including scholarly databases, which potentially allows the use of this tool for academic tasks, both quantitative and qualitative. To test its features, five academic tasks are designed: two quantitative (collecting hit count estimates from Google Search and scraping bibliometric indicators from ResearchGate); two qualitative tasks (performing a narrative synthesis of an academic topic and generating a brief academic author profile), and a mixed task (identifying, collecting and describing a list of publications from Google Scholar Profiles). The results show the inability of ChatGPT Search to conduct quantitative tasks correctly, fabricating the results (hallucination). Qualitative tasks are performed with better results; however, errors are detected, which prevent recommending the tool without manual analysis and refinement. Finally, the ability to generate links to scientific publications can open up competition among academic sites to be mentioned in the ChatGPT Search responses, giving rise to Academic Generative Engine Optimization (A-GEO).
• dc.description.sponsorship Study supported by project “Publicized research: new indicators to measure the effects of timely marketing on scholarly evaluation (PRIME TIME)” (PID2022-142569NA-I00), funded by MCIN/AEI/10.13039/501100011033,and by “ERDF A way of making Europe”, and by Project “Parameters and strategies to increase the relevance of media and digital communication in society: curation, visualiza-tion and visibility (CUVICOM)”, funded by MICIN/AEI/PID2021-123579OB-I00 and by FEDER/EU.
• dc.format.mimetype application/pdf
• dc.identifier.citation Font-Julián CI, Orduña-Malea E, Codina L. ChatGPT Search as a tool for scholarly tasks: evolution or devolution? A variant in the gene FUT9 is associated with susceptibility to placental malaria infection. Infonomy. 2024;5(2):e24059. DOI: 10.3145/infonomy.24.059
• dc.identifier.doi http://dx.doi.org/10.3145/infonomy.24.059
• dc.identifier.issn 2990-2290
• dc.identifier.uri http://hdl.handle.net/10230/68854
• dc.language.iso eng
• dc.publisher EPI (El Profesional de la Información)
• dc.relation.ispartof Infonomy. 2024;5(2):e24059
• dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/PID2022-142569NA-I00
• dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/PID2021-123579OB-I00
• dc.rights Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri http://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword Generative artificial intelligence
• dc.subject.keyword AI
• dc.subject.keyword Link analysis
• dc.subject.keyword Web search
• dc.subject.keyword Search engines
• dc.subject.keyword Narrative synthesis
• dc.subject.keyword Information retrieval
• dc.subject.keyword ChatGPT search
• dc.subject.keyword Scholarly tasks
• dc.subject.keyword Academic tasks
• dc.subject.keyword Quantitative vs. qualitative
• dc.subject.keyword Academic Generative Engine Optimization (A-GEO)
• dc.title ChatGPT Search as a tool for scholarly tasks: evolution or devolution?
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/publishedVersion