BERTopic-Based Public Opinion Topic Mining on Graduate Supervisors: A Case Study of Weibo
DOI:
https://doi.org/10.54097/j686rj13Keywords:
Graduate Supervisor, BERTopic, Dynamic Public OpinionAbstract
Weibo public opinion on graduate advisor issues profoundly reflects the structural contradiction between institutional supply and student demands. This study conducted dynamic topic modeling on 187,238 relevant posts from 2017 to 2024 using the BERTopic model, revealing three core findings. First, the topic distribution exhibits significant dual‑track differentiation: academic routines and student mutual aid constitute a stable public opinion baseline, accounting for over 70% of the corpus, with high‑frequency terms such as "thesis" and "graduation" indicating resource competition pressures under the expansion of enrollment policies, while the "outbreak‑plunge" pulse pattern of extreme events confirms the short‑term nature of public opinion. Second, policy interventions follow a clear three‑stage response path; after the issuance of the Guidelines for Advisor Conduct in 2020, the symbolic phase of policy communication and the lagged accountability phase of institutional implementation highlight the risk of "symbolic governance." Third, cross‑topic analysis further exposes systemic contradictions: the infiltration of academic pressure into regional resource issues reveals inter‑institutional resource imbalances, and although the symbolic dissemination of extreme events prompts institutional reflection, it remains constrained by issue fragmentation. The theoretical contribution of this study lies in quantitatively verifying the correlations among higher education expansion, institutional change, and public opinion evolution. Its practical significance lies in providing data support for constructing an early‑warning mechanism for advisor‑student conflicts and optimizing the advisor authority checklist, while also innovatively confirming the effectiveness of BERTopic in short‑text public opinion modeling, thereby promoting a shift in educational governance paradigms from passive response to active intervention.
Downloads
References
[1] Wang, J., Chang, H., & Du, J. (2024). A review of research on basic issues of supervisor–student relationship: Essence, types, and influencing factors. Journal of Graduate Education Research, (02), 93–100.
[2] Zhang, Y., Xue, C., & Xiao, M. (2024). The role ethics of supervisors as the primary responsible person for postgraduate cultivation: Evolutionary logic, conceptual clarification, and functional orientation. Academic Degrees & Graduate Education, (10), 24–30.
[3] Zhang, Y., & Duan, X. (2023). The alienation and restoration of postgraduate supervisor–student relationship from the perspective of discipline. Journal of Graduate Education Research, (04), 20–28.
[4] Meng, S., Shang, J., Zhang, F., et al. (2022). The effects of scientific information dissemination on COVID-19 in social media and influencing factors of crisis response strategy selection: An empirical analysis based on hot microblogs related to scientists. Library and Information Service, 66(13), 91–101.
[5] Gao, C., Jiang, L., & Dong, T. (2024). Topic evolution of health information needs of the elderly based on BERTopic model: A case study of Sina Weibo platform. Information Science, 42(04), 111–118.
[6] Bian, M., & Zhang, Q. (2024). A discussion on the construction of supervisor–student relationship between supervisors and postgraduates from the perspective of social media. Industry and Technology Forum, 23(13), 265–267.
[7] Zhao, S., Zou, Q., & Wu, X. (2025). The connotation, construction, and alienation of doctoral supervisor–student relationship. Academic Degrees & Graduate Education, (01), 47–54.
[8] Wang, Y. (2018). The postgraduate supervisor system in UK top research universities and its implications: A case study of the University of Oxford. Academic Degrees & Graduate Education, (10), 71–77.
[9] Jiang, W., Zhu, X., & Chen, Z. (2022). Towards good governance: Problem review and resolution pathways of supervisor–student conflicts. Academic Degrees & Graduate Education, (10), 48–54.
[10] Cui, X., Li, H., & Su, T. (2024). The impact of supervisory mentoring styles on graduate students' innovation ability: A meta-analytic test. Journal of Graduate Education Research, (05), 92–99.
[11] Luo, P. (2021). A study on the dynamic mechanism of communication between postgraduates and supervisors from the perspective of interaction ritual chain theory. Academic Degrees & Graduate Education, (03), 21–26.
[12] Zhang, J., & Zhang, Q. (2021). Collaborative education between postgraduate supervisors and counselors: Value implications, practical dilemmas, and pathway choices. Journal of Graduate Education Research, (01), 22–28.
[13] Zou, B., & Qiu, X. (2023). An exploration of supervisor–student relationship and rights–responsibilities cognition in postgraduate education. Guandong Journal, (06), 37–47.
[14] Yin, D., Huang, J., & Qu, Y. (2021). Reform, effectiveness, and reflections on the doctoral supervisor selection system: Based on Peking University's exploration and practice. Academic Degrees & Graduate Education, (05), 16–20.
[15] Liu, J., Zhang, L., & Hu, W. (2025). Research on the current status and optimization strategies of postgraduate supervisor training system in universities in the new era. Academic Degrees & Graduate Education, (04), 31–38.
[16] Cui, J., Du, W., Guan, Y., et al. (2017). An evolution analysis of LDA topic model for personalized recommendation of microblog users. Information Science, 35(08), 3–10.
[17] Miao, H., Quan, Q., & Shu, X. (2025). Topic recognition and quantitative analysis of science and technology talent policy texts based on BERTopic: A case study of the three northeastern provinces. Journal of Modern Information, 45(04), 110–121.
[18] Grootendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv Preprint, arXiv:2203.05794.
[19] Liu, X., Yan, Y., & Zha, X. (2025). Topic modeling research on artificial intelligence application scenarios based on BERTopic. Library & Information, (03), 46–55.
[20] McInnes, L., Healy, J., Saul, N., et al. (2018). UMAP: Uniform manifold approximation and projection. The Journal of Open Source Software, 3(29), 861.
[21] Campello, R. J. G. B., Moulavi, D., Zimek, A., et al. (2015). HDBSCAN: Hierarchical density based clustering. Journal of Machine Learning Research, 16, 1–47.
[22] Liu, H., & Ma, J. (2025). Quality assurance demands and path innovation after postgraduate enrollment expansion. Higher Education Exploration, (01), 78–86.
[23] Xia, Y. (2019). An "attenuation-transfer" model of netizen sentiment based on public opinion big data and its empirical study. Journal of Intelligence, 38(03), 148–154.
[24] Liu, H. (2018). Research on the implementation blockage of ideological and political education policy in higher education based on Smith's model [Master’s thesis].
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Education and Humanities
This work is licensed under a Creative Commons Attribution 4.0 International License.
