Keywords
bibliometric analysis
clustering algorithms
BERT
data visualization
case study (AI in education)
How to Cite
Abstract
Understanding the structure of scientific knowledge and collaboration networks is essential for guiding research and policy decisions. Traditional bibliometric methods, based on keyword co-occurrence and network analysis, often face challenges related to semantic ambiguity and inconsistent terminology, which can obscure thematic patterns and collaborative links. This study examines the potential of BERT-based language models to address these limitations and improve bibliometric mapping. Using a dataset of 504 publications on artificial intelligence in education indexed in Scopus, we compared conventional VOSviewer clustering with BERT-enhanced preprocessing. The integration of BERT significantly improved semantic grouping by consolidating synonymous and morphologically varied terms, reducing keyword redundancy by 17% and increasing graph density, which resulted in clearer thematic clusters and more interpretable collaboration networks. These improvements revealed emerging research trends, such as ethical implications of AI and the growing role of generative models in education, while highlighting central institutions that act as global knowledge hubs. The findings demonstrate that BERT-based preprocessing not only enhances the accuracy and readability of bibliometric visualizations but also supports strategic decision-making in research management. Practical implications include the design of interdisciplinary curricula, the informed allocation of research funding, and the development of agile policies for the responsible adoption of AI. Beyond education, this approach can be applied to domains characterized by terminological complexity, such as healthcare, sustainability, and social sciences. By combining BERT with established bibliometric tools, researchers can achieve a cost-efficient, reproducible, and semantically robust method for mapping scientific landscapes and identifying collaboration opportunities.
References
[1] M. Bond et al., “A meta systematic review of artificial intelligence in higher education: a call for increased ethics, collaboration, and rigour,” Int. J. Educ.al Technol. Higher Educ., vol. 21, no. 1, Jan. 2024. https://doi.org/10.1186/s41239-023-00436-z. Accessed: Oct. 25, 2025. (in English)
[2] H. Crompton and D. Burke, “Artificial intelligence in higher education: the state of the field”, Int. J. Educ.al Technol. Higher Educ., vol. 20, no. 1, Apr. 2023. https://doi.org/10.1186/s41239-023-00392-8. Accessed: Oct. 25, 2025. (in English)
[3] W. Hassan and A. Duarte, “Bibliometric Analysis: A Few Suggestions”, Current Problems in Cardiology, 2024. https://doi.org/10.1016/j.cpcardiol.2024.102640. Accessed: Oct. 25, 2025. (in English)
[4] P. Dubey, P. Dubey, P. K. Agrawal, H. Chourasia, M. Nayak, and H. Gehani, “Bibliometric Analysis of Data Science Research: A Decade of Insights from Web of Science,” in 2023 Fourth Int. Conf. Smart Technol. Comput., Elect. Electron. (ICSTCEE), Bengaluru, India, Dec. 8–9, 2023. IEEE, 2023. https://doi.org/10.1109/icstcee60504.2023.10585030. Accessed: Oct. 25, 2025. (in English)
[5] O. H. Kuzminska, M. S. Mazorchuk, O. V. Barna, and S. Sydorenko, “Bibliometric analysis in determining the research directions of early career researchers”, Inf. Technol. Learn. Tools, vol. 91, no. 5, pp. 113–129, Oct. 2022. https://doi.org/10.33407/itlt.v91i5.4944. Accessed: Oct. 25, 2025. (in English)
[6] K. Çolak and S. Koç, “Bibliometric analysis and mapping with Vosviewer in neet-head research in social sciences,” J. Ekonomi, Dec. 2023. https://doi.org/10.58251/ekonomi.1380379. Accessed: Oct. 25, 2025. (in English)
[7] R. E. Cramarenco, M. I. Burcă-Voicu, and D.-C. Dabija, “Student Perceptions of Online Education and Digital Technologies during the COVID-19 Pandemic: A Systematic Review,” Electronics, vol. 12, no. 2, p. 319, Jan. 2023. https://doi.org/10.3390/electronics12020319. Accessed: Oct. 25, 2025. (in English)
[8] O. Kuzminska, N. Morze, and E. Smyrnova-Trybulska, E. (2022). “Artificial Intelligence in Education: A Study on Using Bibliometric Systems,” In M.Turcani, Z.Balagh (Eds.), Conference Proceedings DIVAI2022, 2-4 May 2022, Sturovo, Slovakia, (pp.393-403), DIVAI 2022 – The 14th international scientific conference on Distance Learning in Applied Informatics. ISSN 2464-7489. (in English)
[9] O. Kuzminska, N. Morze, and E. Smyrnova-Trybulska, “Microlearning as an Educational Technology: Information Requests and Bibliometric Analysis,” in Microlearning. Cham: Springer Int. Publishing, 2022, pp. 27–41. https://doi.org/10.1007/978-3-031-13359-6_2. Accessed: Oct. 25, 2025. (in English)
[10] E. N. S. Patty, Yorman, T. C. Miswaty, A. Syahid, and Muti'ah, “Bibliometric analysis of the use of VOSviewer in educational research: Trends and implications,” Cypriot J. Educational Sci., vol. 19, no. 1, pp. 61–76, Jan. 2024. https://doi.org/10.18844/cjes.v19i1.9376. Accessed: Oct. 25, 2025. (in English)
[11] F. Ju, “Mapping the Knowledge Structure of Image Recognition in Cultural Heritage: A Scientometric Analysis Using CiteSpace, VOSviewer, and Bibliometrix,” J. Imag., vol. 10, no. 11, p. 272, Oct. 2024. https://doi.org/10.3390/jimaging10110272 . Accessed: Oct. 25, 2025. (in English)
[12] S. Rochman et. al., “How Bibliometric Analysis Using VOSviewer Based on Artificial Intelligence Data (using ResearchRabbit Data): Explore Research Trends in Hydrology Content,” ASEAN J. Sci. Eng., vol. 4, no. 2, pp. 251–294, Aug. 2024, [Online]. Available: https://ejournal.kjpupi.id/index.php/ajse/article/view/384. Accessed: Oct. 25, 2025. (in English)
[13] M. Deepa et. al., “Bidirectional Encoder Representations from Transformers (BERT) Language Model for Sentiment Analysis task: Review,” Turkish Journal of Computer and Mathematics Education (TURCOMAT), vol. 12, no. 7, pp. 1708–1721, Apr. 2021. [Online]. Available:https://turcomat.org/index.php/turkbilmat/article/view/3055 Accessed: Oct. 25, 2025. (in English)
[14] S. Yeasmin, N. .Afrin, and M.R. Huq, “Transformer-Based Text Clustering for Newspaper Articles,” In: Satu, M.S., Moni, M.A., Kaiser, M.S., Arefin, M.S. (eds) Machine Intelligence and Emerging Technologies. MIET 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, Springer, Cham, vol. 490, pp. 443-457, 11 June 2023. https://doi.org/10.1007/978-3-031-34619-4_35. Accessed: Oct. 25, 2025. (in English)
[15] A. Subakti, H. Murfi, and N. Hariadi, “The performance of BERT as data representation of text clustering,” J. Big Data, vol. 9, no. 1, Feb. 2022. https://doi.org/10.1186/s40537- 022-00564-9. Accessed: Oct. 25, 2025. (in English)
[16] A. Eklund, M. Forsman, and F. Drewes, “Empirical Configuration Study of a Common Document Clustering Pipeline,” Northern Eur. J. Lang. Technol., vol. 9, no. 1, Sep. 2023. https://doi.org/10.3384/nejlt.2000-1533.2023.4396. Accessed: Oct. 25, 2025. (in English)
[17] B. Yin, M. Zhao, L. Guo, and L. Qiao, “Sentence-BERT and k-means Based Clustering Technology for Scientific and Technical Literature,” in 2023 15th Int. Conf. Comput. Res. Develop. (ICCRD), Hangzhou, China, Jan. 10–12, 2023. IEEE, 2023. https://doi.org/10.1109/ICCRD56364.2023.10080830. Accessed: Oct. 25, 2025. (in English)
[18] R. Hosokawa, J. Yamato, R. Higashinaka, G. Kikui and H.Sugiyama, “Reference Classification Using BERT Models to Support Scientific-Document Writing,” Lecture Notes in Computer Science, Springer, Cham, vol 14644, pp. 167-183. 2024, https://doi.org/10.1007/978-3-031-60511-6_11 . Accessed: Oct. 25, 2025. (in English)
[19] H. Arruda, E. R. Silva, M. Lessa, D. Proença Jr., and R. Bartholo, “VOSviewer and Bibliometrix,” J. Med. Library Assoc., vol. 110, no. 3, pp. 392–395, Dec. 2022. https://doi.org/10.5195/jmla.2022.1434. Accessed: Oct. 25, 2025. (in English)
[20] M. Adrian and M. Muntazimah, “Bibliometric Analysis with the Vosviewer-Based Keyword ‘Mathematical Abilities’”, Proceedings Series on Social Sciences Humanities, vol. 13, pp. 74–80, Nov. 2023. [Online]. Available: https://conferenceproceedings.ump.ac.id/pssh/article/view/885. Accessed: Oct. 25, 2025. (in English)
[21] M. R. Padwiansyah, R. S. Wahyuningsih, and S. D. Handayani, “Analyzing sustainable organizational development with VOSviewer: a bibliometric analysis,” Multidisciplinary Rev., vol. 6, no. 3, p. 2023023, Sep. 2023. https://doi.org/10.31893/multirev.2023023. Accessed: Oct. 25, 2025. (in English)
[22] T. Wolf et al., “Trans formers: State-of-the-Art Natural Language Processing,” In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38-45, Oct. 2020. [Online]. Available: https://aclanthology.org/2020.emnlp-demos.6/ Accessed: Oct. 25, 2025. (in English)
[23] Q. Zheng et al., “Past, present and future of living systematic review: a bibliometrics analysis,” BMJ Glob. Health, vol. 7, no. 10, Oct. 2022, Art. no. e009378. https://doi.org/10.1136/bmjgh-2022-009378 . Accessed: Oct. 25, 2025. (in English)
[24] H.C. Chu, G.H. Hwang, Y.F. Tu, and K.H. Yang, “Roles and research trends of artificial intelligence in higher education: A systematic review of the top 50 most-cited articles,” Australasian Journal of Educational Technology, vol. 38, no. 3, pp. 22–42, 2022. https://doi.org/10.14742/ajet.7526. Accessed: Oct. 25, 2025. (in English)
[25] Cybermetrics Lab. Ranking Web of Universities. Retrieved December 28, 2024. [Online]. Available: https://www.webometrics.info/en. Accessed: Oct. 25, 2025. (in English)
[26] U.A. Bukar, Md, S. Sayeed, S.F.A. Razak, S. Yogarayan, O.A. Amodu and R.A.R. Mah-mood, “A method for analyzing text using VOSviewer,” MethodsX, 11:102339-102339, 2023. https://doi.org/10.1016/j.mex.2023.102339. Accessed: Oct. 25, 2025. (in English)
[27] A. Almalawi, B. Soh, A. Li and H. Samra, “Predictive Models for Educational Purposes: A Systematic Review,” Big Data and Cognitive Computing, vol. 8, no. 12, p. 187, Jul. 2024. https://doi.org/10.3390/bdcc8120187. Accessed: Oct. 25, 2025. (in English)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright (c) 2025 Olena Kuzminska, Eugenia Smyrnova-Trybulska, Malgorzata Przybyła-Kasperek, Filip Smyczek, Nataliia Morze