IDEAS home Printed from https://ideas.repec.org/a/spr/scient/v129y2024i4d10.1007_s11192-024-04939-y.html
   My bibliography  Save this article

Can ChatGPT be used to predict citation counts, readership, and social media interaction? An exploration among 2222 scientific abstracts

Author

Listed:
  • Joost Winter

    (Delft University of Technology)

Abstract

This study explores the potential of ChatGPT, a large language model, in scientometrics by assessing its ability to predict citation counts, Mendeley readers, and social media engagement. In this study, 2222 abstracts from PLOS ONE articles published during the initial months of 2022 were analyzed using ChatGPT-4, which used a set of 60 criteria to assess each abstract. Using a principal component analysis, three components were identified: Quality and Reliability, Accessibility and Understandability, and Novelty and Engagement. The Accessibility and Understandability of the abstracts correlated with higher Mendeley readership, while Novelty and Engagement and Accessibility and Understandability were linked to citation counts (Dimensions, Scopus, Google Scholar) and social media attention. Quality and Reliability showed minimal correlation with citation and altmetrics outcomes. Finally, it was found that the predictive correlations of ChatGPT-based assessments surpassed traditional readability metrics. The findings highlight the potential of large language models in scientometrics and possibly pave the way for AI-assisted peer review.

Suggested Citation

  • Joost Winter, 2024. "Can ChatGPT be used to predict citation counts, readership, and social media interaction? An exploration among 2222 scientific abstracts," Scientometrics, Springer;Akadémiai Kiadó, vol. 129(4), pages 2469-2487, April.
    • Handle: RePEc:spr:scient:v:129:y:2024:i:4:d:10.1007_s11192-024-04939-y
    DOI: 10.1007/s11192-024-04939-y
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s11192-024-04939-y
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.
    File URL: https://libkey.io/10.1007/s11192-024-04939-y?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Sergio Jimenez & Youlin Avila & George Dueñas & Alexander Gelbukh, 2020. "Automatic prediction of citability of scientific articles by stylometry of their titles and abstracts," Scientometrics, Springer;Akadémiai Kiadó, vol. 125(3), pages 3187-3232, December.
    2. Juan Xie & Kaile Gong & Ying Cheng & Qing Ke, 2019. "The correlation between paper length and citations: a meta-analysis," Scientometrics, Springer;Akadémiai Kiadó, vol. 118(3), pages 763-786, March.
    3. Lu, Chao & Bu, Yi & Dong, Xianlei & Wang, Jie & Ding, Ying & Larivière, Vincent & Sugimoto, Cassidy R. & Paul, Logan & Zhang, Chengzhi, 2019. "Analyzing linguistic complexity and scientific impact," Journal of Informetrics, Elsevier, vol. 13(3), pages 817-829.
    4. Christophe Croux & Catherine Dehon, 2010. "Influence functions of the Spearman and Kendall correlation measures," Statistical Methods & Applications, Springer;Società Italiana di Statistica, vol. 19(4), pages 497-515, November.
    5. Dag W. Aksnes & Liv Langfeldt & Paul Wouters, 2019. "Citations, Citation Indicators, and Research Quality: An Overview of Basic Concepts and Theories," SAGE Open, , vol. 9(1), pages 21582440198, February.
    6. Cristina M Pulido & Gisela Redondo-Sama & Teresa Sordé-Martí & Ramon Flecha, 2018. "Social impact in social media: A new method to evaluate the social impact of research," PLOS ONE, Public Library of Science, vol. 13(8), pages 1-20, August.
    7. Akella, Akhil Pandey & Alhoori, Hamed & Kondamudi, Pavan Ravikanth & Freeman, Cole & Zhou, Haiming, 2021. "Early indicators of scientific impact: Predicting citations with altmetrics," Journal of Informetrics, Elsevier, vol. 15(2).
    8. Vera Sommer & Klaus Wohlrabe, 2017. "Citations, journal ranking and multiple authorships reconsidered: evidence from almost one million articles," Applied Economics Letters, Taylor & Francis Journals, vol. 24(11), pages 809-814, June.
    9. Dowling, Michael & Hammami, Helmi & Zreik, Ousayna, 2018. "Easy to read, easy to cite?," Economics Letters, Elsevier, vol. 173(C), pages 100-103.
    10. Stefanie Haustein & Isabella Peters & Judit Bar-Ilan & Jason Priem & Hadas Shema & Jens Terliesner, 2014. "Coverage and adoption of altmetrics sources in the bibliometric community," Scientometrics, Springer;Akadémiai Kiadó, vol. 101(2), pages 1145-1163, November.
    11. Shan Wang & Xiaojun Liu & Jie Zhou, 2022. "Readability is decreasing in language and linguistics," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(8), pages 4697-4729, August.
    12. Mike Thelwall, 2018. "Early Mendeley readers correlate with later citation counts," Scientometrics, Springer;Akadémiai Kiadó, vol. 115(3), pages 1231-1240, June.
    13. Saeed-Ul Hassan & Mubashir Imran & Uzair Gillani & Naif Radi Aljohani & Timothy D. Bowman & Fereshteh Didegah, 2017. "Measuring social media activity of scientific literature: an exhaustive comparison of scopus and novel altmetrics big data," Scientometrics, Springer;Akadémiai Kiadó, vol. 113(2), pages 1037-1057, November.
    14. Ante, Lennart, 2022. "The relationship between readability and scientific impact: Evidence from emerging technology discourses," Journal of Informetrics, Elsevier, vol. 16(1).
    15. Bornmann, Lutz, 2014. "Do altmetrics point to the broader impact of research? An overview of benefits and disadvantages of altmetrics," Journal of Informetrics, Elsevier, vol. 8(4), pages 895-903.
    16. Derya Akcan & Susanna Axelsson & Christina Bergh & Thomas Davidson & Måns Rosén, 2013. "Methodological quality in clinical trials and bibliometric indicators: no evidence of correlations," Scientometrics, Springer;Akadémiai Kiadó, vol. 96(1), pages 297-303, July.
    17. Anqi Ma & Yu Liu & Xiujuan Xu & Tao Dong, 2021. "A deep-learning based citation count prediction model with paper metadata semantic features," Scientometrics, Springer;Akadémiai Kiadó, vol. 126(8), pages 6803-6823, August.
    18. Xueying Liu & Haoran Zhu, 2023. "Linguistic positivity in soft and hard disciplines: temporal dynamics, disciplinary variation, and the relationship with research impact," Scientometrics, Springer;Akadémiai Kiadó, vol. 128(5), pages 3107-3127, May.
    19. James Hartley, 2016. "Erratum to: Is time up for the Flesch measure of reading ease?," Scientometrics, Springer;Akadémiai Kiadó, vol. 109(3), pages 2329-2329, December.
    20. Lutz Bornmann, 2015. "Alternative metrics in scientometrics: a meta-analysis of research into three altmetrics," Scientometrics, Springer;Akadémiai Kiadó, vol. 103(3), pages 1123-1144, June.
    21. Iman Tahamtan & Askar Safipour Afshar & Khadijeh Ahamdzadeh, 2016. "Factors affecting number of citations: a comprehensive review of the literature," Scientometrics, Springer;Akadémiai Kiadó, vol. 107(3), pages 1195-1225, June.
    22. repec:plo:pone00:0120495 is not listed on IDEAS
    23. Zongrui Pei & Junqi Yin & Peter K. Liaw & Dierk Raabe, 2023. "Author Correction: Toward the design of ultrahigh-entropy alloys via mining six million texts," Nature Communications, Nature, vol. 14(1), pages 1-1, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Kayvan Kousha & Mike Thelwall, 2024. "Factors associating with or predicting more cited or higher quality journal articles: An Annual Review of Information Science and Technology (ARIST) paper," Journal of the Association for Information Science & Technology, Association for Information Science & Technology, vol. 75(3), pages 215-244, March.
    2. Xi Zhao & Li Li & Wei Xiao, 2023. "The diachronic change of research article abstract difficulty across disciplines: a cognitive information-theoretic approach," Palgrave Communications, Palgrave Macmillan, vol. 10(1), pages 1-12, December.
    3. Sergio Copiello, 2020. "Other than detecting impact in advance, alternative metrics could act as early warning signs of retractions: tentative findings of a study into the papers retracted by PLoS ONE," Scientometrics, Springer;Akadémiai Kiadó, vol. 125(3), pages 2449-2469, December.
    4. Ying Guo & Xiantao Xiao, 2022. "Author-level altmetrics for the evaluation of Chinese scholars," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(2), pages 973-990, February.
    5. Mingyang Wang & Zhenyu Wang & Guangsheng Chen, 2019. "Which can better predict the future success of articles? Bibliometric indices or alternative metrics," Scientometrics, Springer;Akadémiai Kiadó, vol. 119(3), pages 1575-1595, June.
    6. Wan Siti Nur Aiza & Liyana Shuib & Norisma Idris & Nur Baiti Afini Normadhi, 2024. "Features, techniques and evaluation in predicting articles’ citations: a review from years 2010–2023," Scientometrics, Springer;Akadémiai Kiadó, vol. 129(1), pages 1-29, January.
    7. Hyejin Park & Han Woo Park, 2018. "Research evaluation of Asian countries using altmetrics: comparing South Korea, Japan, Taiwan, Singapore, and China," Scientometrics, Springer;Akadémiai Kiadó, vol. 117(2), pages 771-788, November.
    8. Solanki Gupta & Vivek Kumar Singh & Sumit Kumar Banshal, 2024. "Altmetric data quality analysis using Benford’s law," Scientometrics, Springer;Akadémiai Kiadó, vol. 129(7), pages 4597-4621, July.
    9. Qian Wang & Guangwei Hu, 2024. "Expressions of confusion in research articles: a diachronic cross-disciplinary investigation," Scientometrics, Springer;Akadémiai Kiadó, vol. 129(1), pages 445-471, January.
    10. Stefano Mammola & Elena Piano & Alberto Doretto & Enrico Caprio & Dan Chamberlain, 2022. "Measuring the influence of non-scientific features on citations," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(7), pages 4123-4137, July.
    11. Li, Hao & Hou, Jianhua, 2024. "Revalidation of the applicability of Altmetrics indicators in article-level evaluation: An empirical analysis of papers of different types of citation trajectories," Journal of Informetrics, Elsevier, vol. 18(4).
    12. Giovanni Abramo & Ciriaco Andrea D’Angelo & Leonardo Grilli, 2024. "The role of non-scientific factors vis-à-vis the quality of publications in determining their scholarly impact," Scientometrics, Springer;Akadémiai Kiadó, vol. 129(8), pages 5003-5019, August.
    13. Jianhua Hou & Da Ma, 2020. "How the high-impact papers formed? A study using data from social media and citation," Scientometrics, Springer;Akadémiai Kiadó, vol. 125(3), pages 2597-2615, December.
    14. Ni Cheng & Ke Dong, 2018. "Knowledge communication on social media: a case study of Biomedical Science on Baidu Baike," Scientometrics, Springer;Akadémiai Kiadó, vol. 116(3), pages 1749-1770, September.
    15. Sun, Zhuanlan & He, Dongjin & Li, Yiwei, 2024. "How the readability of manuscript before journal submission advantages peer review process: Evidence from biomedical scientific publications," Journal of Informetrics, Elsevier, vol. 18(3).
    16. Steffen Lemke & Max Brede & Sophie Rotgeri & Isabella Peters, 2022. "Research articles promoted in embargo e-mails receive higher citations and altmetrics," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(1), pages 75-97, January.
    17. Cristina López-Duarte & Marta M. Vidal-Suárez & Belén González-Díaz, 2019. "Cross-national distance and international business: an analysis of the most influential recent models," Scientometrics, Springer;Akadémiai Kiadó, vol. 121(1), pages 173-208, October.
    18. S. Ravikumar & Bidyut Bikash Boruah & M. N. Ravikumar, 2022. "Correlation study between citation count and Mendeley readership of the articles of Sri Lankan authors," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(8), pages 4873-4885, August.
    19. Wanjun Xia & Tianrui Li & Chongshou Li, 2023. "A review of scientific impact prediction: tasks, features and methods," Scientometrics, Springer;Akadémiai Kiadó, vol. 128(1), pages 543-585, January.
    20. Xuan Zhen Liu & Hui Fang, 2017. "What we can learn from tweets linking to research papers," Scientometrics, Springer;Akadémiai Kiadó, vol. 111(1), pages 349-369, April.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:scient:v:129:y:2024:i:4:d:10.1007_s11192-024-04939-y. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.