Semantic clustering technique to identify the signs of extremism in text information
DOI: 10.21293/1818-0442-2024-27-4-141-149
Abstract: This article is devoted to the method of semantic clustering of texts for its subsequent application when solving information security problems. In particular, the technique can be used to identify false and malicious text information prohibited by the legislation of the Russian Federation, propaganda of extremism and terrorism, calls to incite ethnic, religious and other hatred and discord. The method proposed in the article is based on modern BERTopic technology with experimentally selected parameters and algorithms. The methodology was evaluated on data sets containing calls for extremism, terrorism, and incitement of religious and ethnic hatred. The quality metrics used were the silhouette coefficient, the Kalinski–Harabase index, and the Davis–Boldin index. According to the obtained results, the HDBSCAN algorithm was chosen for clustering using the Euclidean metric, the LaBSE algorithm was selected for text representation, and the UMAP algorithm was employed for dimensionality reduction based on the Jaccard metric. This BERTopic configuration resulted in average scores of 0.68 for the silhouette coefficient, 0.36 for the DavisBoldin index, and 136.49 for the Kalinsky–Harabase index.
Keywords: semantics, clustering, information security
Funding: This work was supported by the Ministry of Science and Higher Education of the Russian Federation as part of the core part of the state assignment to TUSUR for 2023–2025 (project no. FEWM2023-0015).
For citation:
Romanov A. S. Semantic clustering technique to identify the signs of extremism in text information. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2024, vol. 27, no. 4, pp. 141–149. DOI: 10.21293/1818-0442-2024-27-4-141-149
Authors and copyright holders:
- Romanov A. S. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
- 1. Li T., Rezaeipanah A. An ensemble agglomerative hierarchical clustering algorithm based on clusters clustering technique and the novel similarity. Journal of King Saud University, 2022, vol. 34, no. 6, pp. 3828–3842.
- 2. McInnes L., Healy J. Accelerated Hierarchical Density Based Clustering. 2017 IEEE International Conference on Data Mining Workshops (ICDMW), New Orleans, LA, USA, 2017, pp. 33–42.
- 3. K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data. Information Sciences, 2023, vol. 622, pp. 178–210.
- 4. Gaussian Mixture Model clustering algorithm for a probabilistic shaping 64QAM coherent optical communication system. 2021 Asia Communications and Photonics Conference (ACP), Shanghai, China, 2021, pp. 1–3.
- 5. Das M., Alphonse P., Kamalanathan S. Markov Clustering Algorithms and Their Application in Analysis of PPI Network of Malaria Genes. 2021 - 11th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Cracow, Poland, 2021, pp. 855–860.
- 6. A Brief Review of Nearest Neighbor Algorithm for Learning and Classification. 2019 International Conference on Intelligent Computing and Control Systems (ICCS), Madurai, India, 2019, pp. 1255–1260.
- 7. Chen L., Cheng Y., Qin J. The research on text clustering based on LDA joint model. Journal of Intelligent & Fuzzy Systems, 2021, vol. 32, pp. 3655–3667.
- 8. Melody K. Extending the Kohonen self-organizing map networks for clustering analysis. Computational Statistics & Data Analysis, 2001, vol. 38, pp. 161–180.
- 9. Saha R. Influence of various text embeddings on clustering performance in NLP. Available at: https://arxiv.org/pdf/2305.03144v1.pdf, free (Accessed: December 08, 2023).
- 10. Author Clustering and Topic Estimation for Short Texts. Available at: https://arxiv.org/pdf/2106.09533v2.pdf, free (Accessed: December 08, 2023).
- 11. Samizadeh M. Graph-based Semantical Extractive Text Analysis. Available at: https://arxiv.org/pdf/2212.09701v1.pdf, free (Accessed: December 08, 2023).
- 12. How Many Topics? Stability Analysis for Topic Models. Available at: https://arxiv.org/pdf/1404.4606v3.pdf, free (Accessed: December 08, 2023).
- 13. Document Clustering based on Topic Maps. Available at: https://arxiv.org/ftp/arxiv/papers/1112/1112.6219.pdf, free (Accessed: December 08, 2023).
- 14. Learning Topics using Semantic Locality. Available at: https://arxiv.org/pdf/1804.04205.pdf, free (Accessed: December 08, 2023).
- 15. Grootendorst M. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. Available at: https://arxiv.org/pdf/2203.05794v1.pdf, free (Accessed: December 08, 2023).
- 16. How ISIS Uses Twitter. Available at: https://www.kaggle.com/datasets/fifthtribe/how-isis-uses-twitter, free (Accessed: December 08, 2023).
- 17. Religious Texts Used By. Available at: https://www.kaggle.com/datasets/fifthtribe/isis-religious-texts, free (Accessed: December 08, 2023).
- 18. Deep_translator’s documentation. Available at: https://deep-translator.readthedocs.io/, free (Accessed: December 08, 2023).
- 19. Dark Web Forums. Available at: https://www.azsecuredata.org/dark-web-forums.html, free (Accessed: December 08, 2023).
- 20. Louvain method. Available at: https://en.wikipedia.org/wiki/Louvain_method, free (Accessed: December 08, 2023).
- 21. Silhouette score. Available at: https://scikit-learn.org/stable/modules/generated/sklearn.metrics.silhouette_score.html, free (Accessed: December 08, 2023).
- 22. Davies-Bouldin score. Available at: https://scikit-learn.org/stable/modules/generated/sklearn.metrics.davies_bouldin_score.html, free (Accessed: December 08, 2023).
- 23. Clinski-Harabasz score. Available at: https://scikitlearn.org/stable/modules/generated/sklearn.metrics.calinski_harabasz_score.html, free (Accessed: December 08, 2023).
- 24. Sentence Transformers. Available at: https://huggingface.co/sentence-transformers, free (Accessed: December 08, 2023).
- 25. UMAP. Available at: https://umap-learn.readthedocs.io/en/latest/, free (Accessed: December 08, 2023).
- 26. HDBSCAN. Available at: https://hdbscan.readthedocs.io/en/latest/how_hdbscan_works.html, free (Accessed: December 08, 2023).
- 27. LaBSE. Available at: https://huggingface.co/sentence-transformers/LaBSE, free (Accessed: December 08, 2023).
Last issue
-2026-1_%D0%BA%D0%BE%D0%BF%D0%B8%D1%8F.jpg)
Editorial office address
Executive Secretary of the Editor’s Office
Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia
Phone / Fax: + 7 (3822) 701-582
Viktor N. Maslennikov
Executive Secretary of the Editor’s Office
Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia
Phone / Fax: + 7 (3822) 51-21-21 / 51-43-02
Subscription for updates
