Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Monitoring the evolution of antisemitic discourse on extremist social media using BERT (2403.05548v1)

Published 6 Feb 2024 in cs.CY, cs.AI, cs.CL, cs.IR, cs.LG, and cs.SI

Abstract: Racism and intolerance on social media contribute to a toxic online environment which may spill offline to foster hatred, and eventually lead to physical violence. That is the case with online antisemitism, the specific category of hatred considered in this study. Tracking antisemitic themes and their associated terminology over time in online discussions could help monitor the sentiments of their participants and their evolution, and possibly offer avenues for intervention that may prevent the escalation of hatred. Due to the large volume and constant evolution of online traffic, monitoring conversations manually is impractical. Instead, we propose an automated method that extracts antisemitic themes and terminology from extremist social media over time and captures their evolution. Since supervised learning would be too limited for such a task, we created an unsupervised online machine learning approach that uses LLMs to assess the contextual similarity of posts. The method clusters similar posts together, dividing, and creating additional clusters over time when sub-themes emerge from existing ones or new themes appear. The antisemitic terminology used within each theme is extracted from the posts in each cluster. Our experiments show that our methodology outperforms existing baselines and demonstrates the kind of themes and sub-themes it discovers within antisemitic discourse along with their associated terminology. We believe that our approach will be useful for monitoring the evolution of all kinds of hatred beyond antisemitism on social platforms.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (26)
  1. A. Schmidt and M. Wiegand, “A survey on hate speech detection using natural language processing,” in SocialNLP@EACL, 2017.
  2. P. Fortuna and S. Nunes, “A survey on automatic detection of hate speech in text,” ACM Computing Surveys (CSUR), vol. 51, pp. 1 – 30, 2018.
  3. F. Poletto, V. Basile, M. Sanguinetti, C. Bosco, and V. Patti, “Resources and benchmark corpora for hate speech detection: a systematic review,” Language Resources and Evaluation, vol. 55, pp. 477 – 523, 2020.
  4. M. S. Jahan and M. Oussalah, “A systematic review of hate speech automatic detection using natural language processing,” Neurocomputing, vol. 546, p. 126232, 2021.
  5. I. Barna and Á. Knap, “An exploration of coronavirus-related online antisemitism in hungary using quantitative topic model and qualitative discourse analysis,” Intersections. East European Journal of Society and Politics, vol. 7, no. 3, pp. 80–100, 2021.
  6. C. Allen, U. Nodelman, and E. N. Zalta, “Stanford encyclopedia of philosophy: a dynamic reference work,” 2003 Joint Conference on Digital Libraries, 2003. Proceedings., pp. 383–, 2003.
  7. L. Wittgenstein, “Philosophical investigations = philosophische untersuchungen,” in PHILOSOPHICAL INVESTIGATIONS, 1958.
  8. E. Rosch, “Principles of categorization,” in Cognitive Science, 1978.
  9. R. Corizzo, M. I. Baron, and N. Japkowicz, “Cpdga: Change point driven growing auto-encoder for lifelong anomaly detection,” Knowl. Based Syst., vol. 247, p. 108756, 2022.
  10. K. Faber, R. Corizzo, B. Sniezynski, and N. Japkowicz, “Vlad: Task-agnostic vae-based lifelong anomaly detection,” Neural networks : the official journal of the International Neural Network Society, vol. 165, pp. 248–273, 2023.
  11. S. Rohlfing and S. J. Sonnenberg, ““who is really british anyway?”: A thematic analysis of responses to online hate materials,” Journal of psychosocial research, vol. 10, p. 2, 2016.
  12. T. Megersa and A. M. Gezie, “Social media users’ online behavior with regard to the circulation of hate speech,” Frontiers in Communication, 2023.
  13. S. Ramaswamy and N. DeClerck, “Customer perception analysis using deep learning and nlp,” Procedia Computer Science, vol. 140, pp. 170–178, 2018.
  14. Á. Aldunate, S. Maldonado, C. Vairetti, and G. Armelini, “Understanding customer satisfaction via deep learning and natural language processing,” Expert Syst. Appl., vol. 209, p. 118309, 2022.
  15. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
  16. A. M. Founta, D. Chatzakou, N. Kourtellis, J. Blackburn, A. Vakali, and I. Leontiadis, “A unified deep learning architecture for abuse detection,” in Proceedings of the 10th ACM conference on web science, pp. 105–114, 2019.
  17. J. Serra, I. Leontiadis, D. Spathis, G. Stringhini, J. Blackburn, and A. Vakali, “Class-based prediction errors to detect hate speech with out-of-vocabulary words,” in Proceedings of the first workshop on abusive language online, pp. 36–40, 2017.
  18. P. Parikh, H. Abburi, N. Chhaya, M. Gupta, and V. Varma, “Categorizing sexism and misogyny through neural approaches,” ACM Transactions on the Web (TWEB), vol. 15, no. 4, pp. 1–31, 2021.
  19. P. Badjatiya, S. Gupta, M. Gupta, and V. Varma, “Deep learning for hate speech detection in tweets,” in Proceedings of the 26th international conference on World Wide Web companion, pp. 759–760, 2017.
  20. M. Chandra, D. Pailla, H. Bhatia, A. Sanchawala, M. Gupta, M. Shrivastava, and P. Kumaraguru, ““subverting the jewtocracy”: Online antisemitism detection using multimodal deep learning,” in Proceedings of the 13th ACM Web Science Conference 2021, pp. 148–157, 2021.
  21. S. Zannettou, J. Finkelstein, B. Bradlyn, and J. Blackburn, “A quantitative approach to understanding online antisemitism,” in Proceedings of the International AAAI conference on Web and Social Media, vol. 14, pp. 786–797, 2020.
  22. M. Ali and S. Zannettou, “Analyzing antisemitism and islamophobia using a lexicon-based approach,” in Workshop Proceedings of the 16th International AAAI Conference on Web and Social Media. Retrieved from https://doi. org/10.36190, 2022.
  23. D. Kikkisetti, R. Ul-Mustafa, W. Melillo, R. Corizzo, Z. Boukouvalas, J. Gill, and N. Japkowicz, “Using llms to discover emerging coded antisemitic hate-speech in extremist social media,” ArXiv, vol. abs/2401.10841, 2024.
  24. S. Ben-David, D. Pál, and H. U. Simon, “Stability of k -means clustering,” in Annual Conference Computational Learning Theory, 2007.
  25. D. Dueck and B. J. Frey, “Non-metric affinity propagation for unsupervised image categorization,” in 2007 IEEE 11th international conference on computer vision, pp. 1–8, IEEE, 2007.
  26. K. G. Derpanis, “Mean shift clustering,” Lecture Notes, vol. 32, pp. 1–4, 2005.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Raza Ul Mustafa (4 papers)
  2. Nathalie Japkowicz (19 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets