Investigating the Use of Sentiment Analysis to Identify Bullying Behaviors in School WhatsApp Groups

• Mannoella Renata L. Pereira Federal University of Paraíba
• Lucas P. Alves Federal University of Paraíba
• Thereza Patrícia P. Padilha Federal University of Paraíba

DOI: https://doi.org/10.5753/sbie.2024.244966

Abstract

Due to the increase in digital communication, cyberbullying has become a critical issue in schools, with various negative impacts as it can affect the well-being and academic performance of victims. Thus, this paper presents ongoing research on the use of sentiment analysis techniques to identify signs of bullying behavior in WhatsApp groups within the school environment. A sentiment classification model is being trained using logistic regression and advanced models such as BERT to identify sentiments and potential bullying behaviors. First results are presented.

Keywords: Sentiment Analysis, Cyberbullying (e-bullying), WhatsApp

References

Church, K.; De Oliveira, R. What's up with WhatsApp? Comparing mobile instant messaging behaviors with traditional SMS. In: Proceedings of the 15th International Conference on Human-Computer Interaction with Mobile Devices and Services. 2013. p. 352-361.

Devlin, J.; Chang, M.; Lee, K.; Toutanova, K. BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1. Minneapolis, 2019. p. 4171-4186.

Liu, B. Sentiment analysis and opinion mining. In: Hirst, G. (Ed.). Synthesis Lectures on Human Language Technologies. San Rafael, CA: Morgan & Claypool Publishers, 2012.

Olweus, D. Bullying at school: What we know and what we can do. Oxford: Blackwell, 1993.

Pang, B.; Lee, L. Opinion mining and sentiment analysis. Foundations and Trends® in Information Retrieval, v. 2, n. 1-2, p. 1-135, 2008.

Paul, S.; Saha, S. CyberBERT: BERT para identificação de cyberbullying. Multimedia Systems, v. 28, p. 1897–1904, 2020.

Pfitscher, Ricardo J.; Camargo, Luiz C.; Moreira, Benjamin G.; Wang, Carolina; Zedral, Rosilaine; Garcia, Tatiana R. Análise de sentimentos em turmas de programação com vistas ao apoio à permanência estudantil. In: Simpósio Brasileiro de Informática na Educação (SBIE), 34. , 2023, Passo Fundo/RS. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 1329-1340. DOI: 10.5753/sbie.2023.234753.

Silva, G. M.; Silva, N. F. F. da; Dias, M. de S. Detecção de bullying: como identificar automaticamente essa prática em redes sociais? Revista de Sistemas de Informação da FSMA, Campos dos Goytacazes, v. 21, p. 11-19, 2018.

Silva, L. N. de C.; Ferrari, D. G. Introdução à mineração de dados. Conceitos básicos, algoritmos e aplicações. 2. ed. São Paulo: Saraiva, 2016. 376p.

Tapia, F.; Aguinaga, C.; Luje, R. Detection of behavior patterns through social networks like Twitter, using data mining techniques as a method to detect cyberbullying. In: 2018 7th International Conference on Software Process Improvement (CIMPS), 2018, p. 111-118. IEEE.

Urtig, L. A. N.; Castro, M. A. N. Análise de sentimentos e suas aplicações na educação: uma revisão de literatura. In: Anais do Simpósio Brasileiro de Informática na Educação, v. 29, n. 1, p. 1002-1011, 2018. Disponível em: [link].