Characterizing the Toxicity of the Brazilian Extremist Communities on Telegram

• Athus Cavalini UFES
• Thamya Donadia UFES
• Giovanni Comarela UFES

DOI: https://doi.org/10.5753/webmedia.2024.243207

Resumo

Telegram has become a central element in discussions related to the ecosystems of information disorder and extremism on social networks. Present on 70% of smartphones in Brazil, the application presents itself as a safe communication space, which began to be used by deplatformed individuals and groups, including extremist groups, who saw the application as a space for building communities and maintaining contact with their audience. In this context, this study presents a characterization of Brazilian extremist communities on Telegram based on the analysis of over 2 million messages broadcast on 128 chats on the platform, focusing on the analysis of the toxicity observed in the content shared in these spaces and its relationship with the conversational dynamics of the groups. The results reveal that these communities share highly toxic messages, including manifestations of hate speech and conspiracy theories, and that the toxicity of the content reflects on its popularity and consequently its spread across the network.

Palavras-chave: Extremism, Toxicity, Telegram, Brazil

Referências

Henrik Axelborn and John Berggren. 2023. Topic Modeling for Customer Insights: A Comparative Analysis of LDA and BERTopic in Categorizing Customer Calls., s. 47 pages.

Athus Cavalini, Fabio Malini, Fabio Gouveia, and Giovanni Comarela. 2023. Politics and disinformation: Analyzing the use of Telegram's information disorder network in Brazil for political mobilization. First Monday (May 2023). DOI: 10.5210/fm.v28i5.12901

Olga V. Chyzh, Mark David Nieman, and Clayton Webb. 2019. The Effects of Dog-Whistle Politics on Political Violence. [link]

Roman Egger and Joanne Yu. 2022. A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts. Frontiers in Sociology 7 (2022). DOI: 10.3389/fsoc.2022.886498

Maarten Grootendorst. 2022. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794 (2022).

Jakob Guhl and Jacob Davey. 2020. A Safe Space to Hate: White Supremacist Mobilisation on Telegram.

Mohamad Hoseini, Philipe Melo, Fabricio Benevenuto, Anja Feldmann, and Savvas Zannettou. 2023. On the Globalization of the QAnon Conspiracy Theory Through Telegram. In Proceedings of the 15th ACM Web Science Conference 2023 (Austin, TX, USA) (WebSci ’23). Association for Computing Machinery, New York, NY, USA, 75–85. DOI: 10.1145/3578503.3583603

Instituto Capixaba de Ensino, Pesquisa e Inovação em Saúde. 2024. Projeto Observa ICEPi. [link] Acessado: 02-01-2024.

Manoel Júnior, Philipe Melo, Daniel Kansaon, Vitor Mafra, Kaio Sa, and Fabricio Benevenuto. 2022. Telegram Monitor: Monitoring Brazilian Political Groups and Channels on Telegram. In Proceedings of the 33rd ACM Conference on Hypertext and Social Media (Barcelona, Spain) (HT ’22). Association for Computing Machinery, New York, NY, USA, 228–231. DOI: 10.1145/3511095.3536375

Alyssa Lees, Vinh Q. Tran, Yi Tay, Jeffrey Sorensen, Jai Gupta, Donald Metzler, and Lucy Vasserman. 2022. A New Generation of Perspective API: Efficient Multilingual Character-level Transformers. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Washington DC, USA) (KDD ’22). Association for Computing Machinery, New York, NY, USA, 3197–3207. DOI: 10.1145/3534678.3539147

Fabio Luiz Malini, Fabio Gomes Goveia, Athus Cavalini, and Francis Sodré. 2023. Padrões da desinformação vacinal no Telegram. In Proc. of IX Congresso Brasileiro de Ciências Sociais e Humanas em Saúde, Suely Deslandes and Marta Verdi (Eds.). Associação Brasileira de Saúde Coletiva, Recife, 46626.

Cynthia Miller-Idriss. 2009. Blood and Culture. Duke University Press, New York, USA. DOI: doi:10.1515/9780822391142

Lawrence Page, Sergey Brin, Rajeev Motwani, and Terry Winograd. 1998. The PageRank Citation Ranking: Bringing Order to the Web. Technical Report. Stanford Digital Library Technologies Project. DOI: 10.1.1.31.1768

Stijn Peeters and Tom Willaert. 2022. Telegram and Digital Methods: Mapping Networked Conspiracy Theories through Platform Affordances. M/C Journal 25, 1 (Mar. 2022). DOI: 10.5204/mcj.2878

Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2022. Robust Speech Recognition via Large-Scale Weak Supervision. DOI: 10.48550/ARXIV.2212.04356

Richard Rogers. 2020. Deplatforming: Following extreme Internet celebrities to Telegram and alternative social media. Media Studies (2020). DOI: 10.1177%2F0267323120922066

Heidi Schulze, Julian Hohner, Simon Greipl, Maximilian Girgnhuber, Isabell Desta, and Diana Rieger. 2022. Far-right conspiracy groups on fringe platforms: a longitudinal analysis of radicalization dynamics on Telegram. Convergence 28, 4 (2022), 1103–1126. DOI: 10.1177/13548565221104977

Fábio Souza, Rodrigo Nogueira, and Roberto Lotufo. 2020. BERTimbau: pretrained BERT models for Brazilian Portuguese. In 9th Brazilian Conference on Intelligent Systems, BRACIS, Rio Grande do Sul, Brazil, October 20-23 (to appear).

Statista. 2023. Telegram messenger global MAU 2014-2023. [link]. Acessado: 31-01-2024.

Samantha Walther and Andrew McCoy. 2021. U.S. Extremism on Telegram: Fueling Disinformation, Conspiracy Theories, and Accelerationism. Perspectives on Terrorism 15, 2 (Apr 2021). [link]

Gabriel Weimann. 2016. Terrorist Migration to the Dark Web. Perspectives on Terrorism 10, 3 (2016), 40–44. [link]