Identificando e categorizando linguagem ofensiva em redes sociais
Resumo
A presença de textos que apresentam discursos de ódio em redes sociais se torna mais evidente a cada dia. A remoção manual de tais textos passa a ser inviável devido ao volume de publicações feitas diariamente. Técnicas de aprendizado de máquina podem ser utilizadas com o objetivo de automatizar a detecção e remoção de tais textos. Esse trabalho tem como objetivo identificar e caracterizar a presença de discurso de ódio em textos da rede social Twitter, utilizando os classificadores Random Forest, SVM linear, RBF e Sigmoid, Naivé Bayes multinomial e Árvore de Decisão. Foi alcançado um F1 score de 0.71 na tarefa de identificação de discurso de ódio e um F1 score 0.54 e 0.49 nas tarefas de categorização do discurso de ódio.
Palavras-chave:
Twitter, redes sociais, árvore de decisão, aprendizado de máquina
Referências
Badjatiya, P., Gupta, S., Gupta, M., and Varma, V. (2017). Deep learning for hate speech detection in tweets. CoRR, abs/1706.00188.
Bird, S., Klein, E., and Loper, E. (2009). Natural Language Processing with Python. O’Reilly Media, Inc., 1st edition.
Davidson, T., Warmsley, D., Macy, M. W., and Weber, I. (2017). Automated hate speech detection and the problem of offensive language. CoRR, abs/1703.04009.
Derczynski, L., Ritter, A., Clark, S., and Bontcheva, K. (2013). Twitter part-of-speech tagging for all: Overcoming sparse and noisy data. In Proceedings of the International Conference Recent Advances in Natural Language Processing RANLP 2013, pages 198–206, Hissar, Bulgaria. INCOMA Ltd. Shoumen, BULGARIA.
Djuric, N., Zhou, J., Morris, R., Grbovic, M., Radosavljevic, V., and Bhamidipati, N. (2015). Hate speech detection with comment embeddings. In Proceedings of the 24th International Conference on World Wide Web, WWW ’15 Companion, pages 29–30, New York, NY, USA. ACM.
Njagi, D., Zuping, Z., Hanyurwimfura, D., and Long, J. (2015). A lexicon-based appro- ach for hate speech detection. International Journal of Multimedia and Ubiquitous Engineering, 10:215–230.
Razavi, A. H., Inkpen, D., Uritsky, S., and Matwin, S. (2010). Offensive language de- tection using multi-level classification. In Proceedings of the 23rd Canadian Confe- rence on Advances in Artificial Intelligence, AI’10, pages 16–27, Berlin, Heidelberg. Springer-Verlag.
Saif, H., He, Y., and Alani, H. (2012). Alleviating data sparsity for twitter sentiment analysis. In 2nd Workshop on Making Sense of Microposts (#MSM2012): Big things come in small packages at the 21st International Conference on theWorld Wide Web (WWW’12), pages 2–9. CEUR Workshop Proceedings (CEUR-WS.org).
Silva, N. F. F. d. (2016). Análise de sentimentos em textos curtos provenientes de redes sociais. PhD thesis, Universidade de São Paulo.
Waseem, Z., Davidson, T., Warmsley, D., and Weber, I. (2017). Understanding abuse: A typology of abusive language detection subtasks. In Proceedings of the First Workshop on Abusive Language Online, pages 78–84. Association for Computational Linguistics.
Waseem, Z. and Hovy, D. (2016). Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In SRW@HLT-NAACL.
Watanabe, H., Bouazizi, M., and Ohtsuki, T. (2018). Hate speech on twitter: A prag- matic approach to collect hateful and offensive expressions and perform hate speech detection. IEEE Access, 6:13825–13835.
Zampieri, M., Malmasi, S., Nakov, P., Rosenthal, S., Farra, N., and Kumar, R. (2019). Pre- dicting the type and target of offensive posts in social media. CoRR, abs/1902.09666.
Bird, S., Klein, E., and Loper, E. (2009). Natural Language Processing with Python. O’Reilly Media, Inc., 1st edition.
Davidson, T., Warmsley, D., Macy, M. W., and Weber, I. (2017). Automated hate speech detection and the problem of offensive language. CoRR, abs/1703.04009.
Derczynski, L., Ritter, A., Clark, S., and Bontcheva, K. (2013). Twitter part-of-speech tagging for all: Overcoming sparse and noisy data. In Proceedings of the International Conference Recent Advances in Natural Language Processing RANLP 2013, pages 198–206, Hissar, Bulgaria. INCOMA Ltd. Shoumen, BULGARIA.
Djuric, N., Zhou, J., Morris, R., Grbovic, M., Radosavljevic, V., and Bhamidipati, N. (2015). Hate speech detection with comment embeddings. In Proceedings of the 24th International Conference on World Wide Web, WWW ’15 Companion, pages 29–30, New York, NY, USA. ACM.
Njagi, D., Zuping, Z., Hanyurwimfura, D., and Long, J. (2015). A lexicon-based appro- ach for hate speech detection. International Journal of Multimedia and Ubiquitous Engineering, 10:215–230.
Razavi, A. H., Inkpen, D., Uritsky, S., and Matwin, S. (2010). Offensive language de- tection using multi-level classification. In Proceedings of the 23rd Canadian Confe- rence on Advances in Artificial Intelligence, AI’10, pages 16–27, Berlin, Heidelberg. Springer-Verlag.
Saif, H., He, Y., and Alani, H. (2012). Alleviating data sparsity for twitter sentiment analysis. In 2nd Workshop on Making Sense of Microposts (#MSM2012): Big things come in small packages at the 21st International Conference on theWorld Wide Web (WWW’12), pages 2–9. CEUR Workshop Proceedings (CEUR-WS.org).
Silva, N. F. F. d. (2016). Análise de sentimentos em textos curtos provenientes de redes sociais. PhD thesis, Universidade de São Paulo.
Waseem, Z., Davidson, T., Warmsley, D., and Weber, I. (2017). Understanding abuse: A typology of abusive language detection subtasks. In Proceedings of the First Workshop on Abusive Language Online, pages 78–84. Association for Computational Linguistics.
Waseem, Z. and Hovy, D. (2016). Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In SRW@HLT-NAACL.
Watanabe, H., Bouazizi, M., and Ohtsuki, T. (2018). Hate speech on twitter: A prag- matic approach to collect hateful and offensive expressions and perform hate speech detection. IEEE Access, 6:13825–13835.
Zampieri, M., Malmasi, S., Nakov, P., Rosenthal, S., Farra, N., and Kumar, R. (2019). Pre- dicting the type and target of offensive posts in social media. CoRR, abs/1902.09666.
Publicado
22/11/2019
Como Citar
BORGES, Cardeque Henrique B. A.; FELIX, Nádia F..
Identificando e categorizando linguagem ofensiva em redes sociais. In: ESCOLA REGIONAL DE INFORMÁTICA DE GOIÁS (ERI-GO), 7. , 2019, Goiânia.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 117-128.
