Incivilidade em Comunidades Brasileiras de Jogos Competitivos no Discord: Limitações da Moderação Automatizada
Resumo
Introdução: As comunidades de jogos online cresceram em larga escala, mas essa expansão foi acompanhada por problemas persistentes de toxicidade e incivilidade, sobretudo em ambientes competitivos. Objetivo: Este artigo investiga como a comunidade brasileira de jogos competitivos se manifesta em servidores do Discord e quais limitações os modelos automáticos de classificação de incivilidades apresentam nesse contexto. Metodologia: A partir do corpus Discord Unveiled, é derivado um subconjunto filtrado de canais de jogos em português brasileiro e construídas duas amostras de mensagens, anotadas com as ferramentas Detoxify e Perspective e avaliadas manualmente. Resultados: Os modelos apresentaram boa concordância geral, mas mostraram vieses relevantes ao lidar com vulgaridades coloquiais, siglas e insultos em código misto.
Palavras-chave:
Jogos online, Discord, Detecção de toxicidade, Incivilidade, Português brasileiro
Referências
Aquino, Y., Bento, P., Buzelin, A., Dayrell, L., Malaquias, S., Santana, C., Estanislau, V., Dutenhefner, P., Evangelista, G. H. G., Porfírio, L. G., Grossi, C. S., Rigueira, P. B., Almeida, V., Pappa, G. L., e Meira Jr., W. (2025). Discord unveiled: A comprehensive dataset of public communication (2015-2024). arXiv preprint arXiv:2502.00627.
Brito, C. R. d. e Ramos, D. K. (2024). Comunidades de jogos digitais: formas de habitar e aprender. Revista e-Curriculum, 22:e61666.
Brito, I. A., Dollis, J. S., Färber, F. B., Silva, D. F. C., e Galvão Filho, A. R. (2025). Toxsyn-pt: A large-scale synthetic dataset for hate speech detection in portuguese. arXiv preprint arXiv:2506.10245.
Fillies, J., Peikert, S., e Paschke, A. (2024). Hateful messages: A conversational data set of hate speech produced by adolescents on discord. In Data Science—Analytics and Applications, pages 37–44. Springer.
Gan, W. et al. (2024). Aggression in online gaming: The role of online disinhibition, social dominance orientation, moral disengagement, and gender traits. Frontiers in Psychology, 15:1480214.
Gibrim, P. T. M., Ribeiro, M. V. G., Moreira, L. S., Melo, P. d. F., e Reis, J. C. S. (2025). I’m not welcome here – uma revisão de escopo sobre toxicidade e discurso de ódio em jogos digitais. In Anais do XXXI Simpósio Brasileiro de Sistemas Multimídia e Web (WebMedia), pages 646–660. SBC.
Gisbert-Pérez, J. et al. (2024). Gender differences in internet gaming among university students: A discriminant analysis. Frontiers in Psychology, 15:1412739.
Hanu, L. e Unitary team (2020). Detoxify. GitHub repository.
Kou, Y. et al. (2025). How do the effects of toxicity in competitive online video games vary by source and outcome? PLOS ONE, 20(6):e0325462.
Leite, J. A., Silva, D. F., Bontcheva, K., e Scarton, C. (2020). Toxic language detection in social media for brazilian portuguese: New dataset and multilingual analysis. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 914–924.
Naseem, U., Shiwakoti, S., Shah, S. B., Thapa, S., e Zhang, Q. (2025). Gametox: A comprehensive dataset and analysis for enhanced toxicity detection in online gaming communities. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, pages 440–447.
Nexø, L. A. et al. (2024). Toxic behaviours in esport: A review of data-collection and toxicity detection methods. International Journal of Esports, 1(1).
Seering, J. (2020). Reconsidering self-moderation: The role of research in supporting community-based models for online content moderation. Proceedings of the ACM on Human-Computer Interaction, 4(CSCW2):1–28.
Sun, X. et al. (2024). Toxic behavior in multiplayer online games: The role of witnessed verbal aggression, game engagement and social self-efficacy. Behaviour & Information Technology.
Trajano, D., Bordini, R. H., e Vieira, R. (2023). Olid-br: offensive language identification dataset for brazilian portuguese. In Language Resources and Evaluation. Springer.
Yang, D. et al. (2023). Unveiling identity biases in toxicity detection: A game-focused dataset and methodological framework. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 271–281.
Zsila, Á., Shabahang, R., Aruguete, M. S., e Orosz, G. (2022). Toxic behaviors in online multiplayer games: Prevalence, perceived severity, and effects on gaming experience. Telematics and Informatics, 73:101856.
Brito, C. R. d. e Ramos, D. K. (2024). Comunidades de jogos digitais: formas de habitar e aprender. Revista e-Curriculum, 22:e61666.
Brito, I. A., Dollis, J. S., Färber, F. B., Silva, D. F. C., e Galvão Filho, A. R. (2025). Toxsyn-pt: A large-scale synthetic dataset for hate speech detection in portuguese. arXiv preprint arXiv:2506.10245.
Fillies, J., Peikert, S., e Paschke, A. (2024). Hateful messages: A conversational data set of hate speech produced by adolescents on discord. In Data Science—Analytics and Applications, pages 37–44. Springer.
Gan, W. et al. (2024). Aggression in online gaming: The role of online disinhibition, social dominance orientation, moral disengagement, and gender traits. Frontiers in Psychology, 15:1480214.
Gibrim, P. T. M., Ribeiro, M. V. G., Moreira, L. S., Melo, P. d. F., e Reis, J. C. S. (2025). I’m not welcome here – uma revisão de escopo sobre toxicidade e discurso de ódio em jogos digitais. In Anais do XXXI Simpósio Brasileiro de Sistemas Multimídia e Web (WebMedia), pages 646–660. SBC.
Gisbert-Pérez, J. et al. (2024). Gender differences in internet gaming among university students: A discriminant analysis. Frontiers in Psychology, 15:1412739.
Hanu, L. e Unitary team (2020). Detoxify. GitHub repository.
Kou, Y. et al. (2025). How do the effects of toxicity in competitive online video games vary by source and outcome? PLOS ONE, 20(6):e0325462.
Leite, J. A., Silva, D. F., Bontcheva, K., e Scarton, C. (2020). Toxic language detection in social media for brazilian portuguese: New dataset and multilingual analysis. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 914–924.
Naseem, U., Shiwakoti, S., Shah, S. B., Thapa, S., e Zhang, Q. (2025). Gametox: A comprehensive dataset and analysis for enhanced toxicity detection in online gaming communities. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, pages 440–447.
Nexø, L. A. et al. (2024). Toxic behaviours in esport: A review of data-collection and toxicity detection methods. International Journal of Esports, 1(1).
Seering, J. (2020). Reconsidering self-moderation: The role of research in supporting community-based models for online content moderation. Proceedings of the ACM on Human-Computer Interaction, 4(CSCW2):1–28.
Sun, X. et al. (2024). Toxic behavior in multiplayer online games: The role of witnessed verbal aggression, game engagement and social self-efficacy. Behaviour & Information Technology.
Trajano, D., Bordini, R. H., e Vieira, R. (2023). Olid-br: offensive language identification dataset for brazilian portuguese. In Language Resources and Evaluation. Springer.
Yang, D. et al. (2023). Unveiling identity biases in toxicity detection: A game-focused dataset and methodological framework. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 271–281.
Zsila, Á., Shabahang, R., Aruguete, M. S., e Orosz, G. (2022). Toxic behaviors in online multiplayer games: Prevalence, perceived severity, and effects on gaming experience. Telematics and Informatics, 73:101856.
Publicado
29/09/2026
Como Citar
MATOS, Thiago Lima; CAPELO, Marina; LOPES, Salete Fontenele; SARAIVA, Diogo; PAIVA, Alicia; PAIXAO, Matheus.
Incivilidade em Comunidades Brasileiras de Jogos Competitivos no Discord: Limitações da Moderação Automatizada. In: SIMPÓSIO BRASILEIRO DE JOGOS E ENTRETENIMENTO DIGITAL (SBGAMES), 25. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 1390-1401.
DOI: https://doi.org/10.5753/sbgames.2026.25870.
