Monitoring Public Opinion on Police Operations in Brazil via YouTube Video Comments

• Saul Sousa da Rocha UFPI
• Carlos Henrique do Vale e Silva UFPI
• Carlos H. G. Ferreira UFMG
• Glauber Dias Gonçalves UFPI
• Jussara Marques de Almeida UFOP

DOI: https://doi.org/10.5753/brasnam.2024.3101

Abstract

In this work, we propose a system that uses user comments on YouTube to monitor people’s perception of police operations in incidents of urban violence with repercussions on this platform. We explore attributes extracted from these comments and natural language processing models, showing the challenges of this inference over two years. Our best models achieved accuracy and macro-F1 of 87% to infer positions of approval, disapproval, and neutrality, in addition to a good generalization capacity across different platforms, evaluated on Twitter/X and YouTube. As a result, we identified periods with dominant positions, which, disregarding neutrality, mostly tend to approve police operations, while disapprovals were identified at regional granularity.

References

Bechini, A., Ducange, P., Marcelloni, F., and Renda, A. (2020). Stance analysis of twitter users: the case of the vaccination topic in italy. IEEE Intelligent Systems, 36(5):131–139.

Brainard, L. and Edlins, M. (2015). Top 10 us municipal police departments and their social media usage. The American Review of Public Administration, 45(6):728–745.

Brown, G. R. (2016). The blue line on thin ice: Police use of force modifications in the era of cameraphones and youtube. British journal of criminology, 56(2):293–312.

Ceron, A. and Negri, F. (2016). The “social side” of public policy: Monitoring online public opinion and its mobilization during the policy cycle. Policy & Internet, 8(2):131–147.

Chakraborty, P. and Sharma, A. (2019). Public opinion analysis of the transportation policy using social media data: a case study on the delhi odd–even policy. Transportation in Developing Economies, 5:1–9.

Chaparro, L. F., Pulido, C., Rudas, J., Reyes, A. M., Victorino, J., Narváez, L. Á., Gómez, F., and Martinez, D. (2020). Sentiment analysis of social network content to characterize the perception of security. In 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pages 685–691. IEEE.

D’Andrea, E., Ducange, P., Bechini, A., Renda, A., and Marcelloni, F. (2019). Monitoring the public opinion about the vaccination topic from tweets analysis. Expert Systems with Applications, 116:209–226.

Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In Association for Computational Linguistics: Human Language Technologies, pages 4171–4186.

El Barachi, M., AlKhatib, M., Mathew, S., and Oroumchian, F. (2021). A novel sentiment analysis framework for monitoring the evolving public opinion in real-time: Case study on climate change. Journal of Cleaner Production, 312:127820.

Feitosa, M. P. F., Ferreira, C. H., Gonçalves, G. D., and de Almeida, J. M. (2022). Análise da percepção das pessoas no twitter sobre ações policiais. In Anais do XI Brazilian Workshop on Social Network Analysis and Mining, pages 73–84. SBC.

Hand, L. C. and Ching, B. D. (2020). Maintaining neutrality: A sentiment analysis of police agency facebook pages before and after a fatal officer-involved shooting of a citizen. Government Information Quarterly, 37(1):101420.

Hossain, T., Logan IV, R. L., Ugarte, A., Matsubara, Y., Young, S., and Singh, S. (2020). Covidlies: Detecting covid-19 misinformation on social media. In Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020.

Junior, J. M. d. R., Linhares, R. S., Ferreira, C. H. G., Nobre, G. P., Murai, F., and Almeida, J. M. (2022). Uncovering discussion groups on claims of election fraud from twitter. In International Conference on Social Informatics, pages 320–336. Springer.

Kocoń, J., Cichecki, I., Kaszyca, O., Kochanek, M., Szydło, D., Baran, J., Bielaniewicz, J., Gruza, M., Janz, A., Kanclerz, K., et al. (2023). Chatgpt: Jack of all trades, master of none. Information Fusion, 99:101861.

Mahesh, B. (2020). Machine learning algorithms-a review. International Journal of Science and Research (IJSR).[Internet], 9:381–386.

Mohammad, S. M., Sobhani, P., and Kiritchenko, S. (2017). Stance and sentiment in tweets. ACM Transactions on Internet Technology (TOIT), 17(3):1–23.

NEV-USP (2024). Monitor da violência. Disponível em: [link]. Acesso em 07 de mar. 2024.

Newman, N., Fletcher, R., Robertson, C. T., Eddy, K., and Nielsen, R. K. (2022). Reuters institute digital news report 2022. Reuters Institute for the study of Journalism.

Ricardo, C. d. M., de Siqueira, P. P., and Marques, C. R. (2013). Estudo conceitual sobre os espaços urbanos seguros. Revista brasileira de segurança pública, 7(1):200–216.

Souza, F., Nogueira, R., and Lotufo, R. (2020). BERTimbau: pretrained BERT models for Brazilian Portuguese. In Brazilian Conference on Intelligent Systems.

Tucker, R., O’Brien, D. T., Ciomek, A., Castro, E., Wang, Q., and Phillips, N. E. (2021). Who ‘tweets’ where and when, and how does it help understand crime rates at places? measuring the presence of tourists and commuters in ambient populations. Journal of Quantitative Criminology, 37(2):333–359.

Wang, M., Wu, H., Zhang, T., and Zhu, S. (2020). Identifying critical outbreak time window of controversial events based on sentiment analysis. Plos one, 15(10):e0241355.

Weinzierl, M., Hopfer, S., and Harabagiu, S. (2021). Misinformation adoption or rejection in the era of covid-19. In Proceedings of the International AAAI Conference on Web and Social Media (ICWSM), AAAI Press.