student from 01.01.2024 to 01.01.2026
Krasnodar, Krasnodar, Russian Federation
student from 01.01.2023 to 01.01.2026
Krasnodar, Krasnodar, Russian Federation
UDC 30
The article presents the results of a comprehensive discourse analysis of a corpus of 595 scientific publications in sociology from 2020–2025, selected from the CyberLeninka online library. The aim of the study is to diagnose the current state, structural features, and dynamics of thematic trends in Russian sociological science using quantitative methods of computational linguistics. The methodology includes automatic data collection, linguistic preprocessing (lemmatization using UDPipe), topic modeling via Latent Dirichlet Allocation (LDA), and analysis of semantic relationships based on GloVe word embeddings with subsequent visualization of semantic networks. The results revealed a stable core of disciplinary discourse formed by theoretical-methodological, historical, and educational concepts. Dynamic analysis showed a significant increase in the relevance of topics related to management, digitalization, data, and technologies starting from 2023. The key finding is the identification of a pronounced semantic gap between this traditional humanities core and the emerging «Digitalization and AI» cluster. This indicates a weak conceptual integration of digital methods and topics into the mainstream discourse of Russian sociology, which retains a predominantly theoretical-reflective character. The study contributes to scientometrics and sociology of knowledge by offering a toolkit for objective mapping and reflection on the development trajectories of social sciences in the context of digital transformation.
text mining, sociology of science, scientific texts, digitalization, topic modeling
1. Medvedev M.M. Kazach'i kolybel'nye pesni: opyt klassifikacii i obobscheniya etnograficheskogo materiala metodami intellektual'nogo analiza teksta / M.M. Medvedev, A.A. Sergeev // Golos minuvshego. – 2024. – № 3. – S. 30–40. – EDN PBTAVZ. – URL: https://www.elibrary.ru/item.asp?id=PBTAVZ (data obrascheniya: 26.01.2026).
2. Nikolina N.V. Diskurs-analiz kak refleksivnaya praktika v sociologii nauchnogo znaniya / N.V. Nikolina // Filosofiya nauki. – 2022. – № 3. – S. 12-20. – URL: http://vital.lib.tsu.ru/vital/access/manager/Repository/koha:000999554 (data obrascheniya: 26.01.2026).
3. Runaev T.A. Intellektual'nyy analiz teksta v social'nyh naukah: uchebnoe posobie / T.A. Runaev; Ministerstvo nauki i vysshego obrazovaniya Rossiyskoy Federacii, Kubanskiy gosudarstvennyy universitet. – Krasnodar: Kubanskiy gos. un-t, 2024. – 127 s. EDN: https://elibrary.ru/YJLRWJ
4. Blei D.M. Latent dirichlet allocation / D.M. Blei, A.Y. Ng, M.I. Jordan // Journal of Machine Learning Research. – 2003. – Vol. 3. – P. 993–1022. – URL: https://www.jmlr.org/papers/volume3/blei03a/blei03a.pdf (data obrascheniya: 26.01.2026).
5. Grimmer J. Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts / J. Grimmer, B.M. Stewart // Political Analysis. – 2013. – Vol. 21, № 3. – P. 267–297. – DOI: https://doi.org/10.1093/pan/mps028. – URL: https://web.stanford.edu/~jgrimmer/tad2.pdf (data obrascheniya: 26.01.2026).
6. Pennington J. GloVe: Global Vectors for Word Representation / J. Pennington, R. Socher, C.D. Manning // Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). – 2014. – P. 1532–1543. – URL: https://aclanthology.org/D14-1162/ (data obrascheniya: 26.01.2026). DOI: https://doi.org/10.3115/v1/D14-1162
7. Straka M. UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing / M. Straka, J. Hajic, J. Strakova // Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016). – Portoroz, Slovenia, 2016. – P. 4290–4297. – URL: https://ufal.mff.cuni.cz/biblio/attachments/2016-straka-p4247732638960608255.pdf (data obrascheniya: 26.01.2026).
