Development of a dataset with comments extracted from Twitch about the game League of Legends

• Lucas D. F. Rodrigues UFOPA http://orcid.org/0000-0001-9280-0547
• Luiz C. C. L. Junior UEMA
• Antonio F. L. Jacob Junior UEMA https://orcid.org/0000-0002-9415-7265
• Fábio M. F. Lobato UFOPA / UEMA https://orcid.org/0000-0002-6282-0368

DOI: https://doi.org/10.5753/brasnam.2021.16128

Abstract

The growth of live streaming platforms like Twitch, driven by the increase in the volume of content creators, has positively impacted an economically important industry, electronic games (e-Sports). The highlight of the category within the Multiplayer Online Battle Arena (MOBA) type goes to the League of Legends, which was one of those responsible for the legitimization and professionalization of e-Sports. The game has a wide range of creators and they bring with them a lot of interactions from the users who watch them. A deleterious phenomenon perceived in this scenario is the proliferation of hate speech, with comments attacking or denigrating people or groups, creating a network of hate. In this work, we present a dataset built with comments extracted from the broadcasts of the creators with greater engagement on the platform, visualizing the characteristic aspects and verifying how hate is distributed. This database has the potential to assist research involving detection and also in the analysis of this industry/application domain of the addressed theme.

Keywords: hate speech, twitch, dataset, league of legends, social media

References

Almeida, G. R., Guimarães, I., Jacob Jr, A. F., & Lobato, F. M. (2020). Fontes de dados gerados por usuários: quais plataformas considerar?. In Anais do IX Brazilian Workshop on Social Network Analysis and Mining (pp. 25-36). SBC.

Atef, N. (2020). Classifying Hate Speech with a pyTorch Transformer.

Coutinho, V. M. D. M. S., & Malheiros, Y. (2020). Detecção de Mensagens Homofóbicas em Português no Twitter usando Análise de Sentimentos. In Anais do IX Brazilian Workshop on Social Network Analysis and Mining (pp. 1-12). SBC.

Deng, J., Tyson, G., Cuadrado, F., & Uhlig, S. (2017). Internet scale user-generated live video streaming: The Twitch case. In International Conference on Passive and Active Network Measurement (pp. 60-71). Springer, Cham.

dos Santos, L. F., & Guedes, G. P. (2019). Identificaçao de predadores sexuais brasileiros por meio de análise de conversas realizadas na internet. In Anais do VIII Brazilian Workshop on Social Network Analysis and Mining (pp. 143-154). SBC.

Erlapally, D. (2020). Hate Speech Detection || 1D CNN || Glove Embedding.

Fortuna, P., & Nunes, S. (2018). A survey on automatic detection of hate speech in text. ACM Computing Surveys (CSUR), 51(4), 1-30.

Fuchs, C. (2021). Social media: A critical introduction. Sage.

Gambäck, B., & Sikdar, U. K. (2017). Using convolutional neural networks to classify hate-speech. In Proceedings of the first workshop on abusive language online (pp. 85-90).

Hilvert-Bruce, Z., Neill, J. T., Sjöblom, M., & Hamari, J. (2018). Social motivations of live-streaming viewer engagement on Twitch. Computers in Human Behavior, 84, 58-67.

Hinnant, N. C. (2013). Practicing work, perfecting play: League of Legends and the sentimental education of e-sports.

Index, P. P. (2019). Twitch python.

Johnson, M. R., & Woodcock, J. (2019). The impacts of live streaming and Twitch. tv on the video game industry. Media, Culture & Society, 41(5), 670-688.

Junior, L. F., Junior, J. S., & Lobato, F. (2020). Um olhar sobre turismo gastronômico: Um caso no TripAdvisor. In Anais do XVII Encontro Nacional de Inteligência Artificial e Computacional (pp. 519-530). SBC.

Lima Jr, L. C. C., Rodrigues, L. D. F., Jacob Jr, A. F. L., and Lobato, F. M. F. (2020). League of Legends and hate speech: a corpus for comments in Twitch.tv.

Moore, M. (2018). 2 Popular Twitch Streamers Banned for a Month Over Hate Speech.

Nascimento, G., Carvalho, F., Cunha, A. M. D., Viana, C. R., & Guedes, G. P. (2019). Hate speech detection using Brazilian imageboards. In Proceedings of the 25th Brazillian Symposium on Multimedia and the Web (pp. 325-328).

Perrin, A. (2015). Social media usage.Pew research center, pages 52–68.

Pitsilis, G. K., Ramampiaro, H., and Langseth, H. (2018). Effective hate-speech detectionin twitter data using recurrent neural networks. Applied Intelligence, 48(12):4730–4742.

Rodrigues, L., Junior, A., & Lobato, F. (2019). Notícias relacionadas a pessoas com deficiência: uma análise do conteúdo gerado pelos usuários em postagens de mídias sociais. In Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional (pp. 811-822). SBC.

Sakhiya, N. (2020). Hate Speech Detection: RNN.

Silva, A., & Roman, N. (2020). Hate Speech Detection in Portuguese with Naïve Bayes, SVM, MLP and Logistic Regression. In Anais do XVII Encontro Nacional de Inteligência Artificial e Computacional (pp. 1-12). SBC.

Wang, C. (2018). Interpreting neural network hate speech classifiers. In Proceedings of the 2nd Workshop on Abusive Language Online (ALW2) (pp. 86-92).

Watanabe, H., Bouazizi, M., & Ohtsuki, T. (2018). Hate speech on twitter: A pragmatic approach to collect hateful and offensive expressions and perform hate speech detection. IEEE access, 6, 13825-13835.

Wei, X., Lin, H., Yang, L., & Yu, Y. (2017). A convolution-LSTM-based deep neural network for cross-domain MOOC forum post classification. Information, 8(3), 92.