A Method to Predict Specific Types of Violence Against Women in Pernambuco

• Arthur Carvalho da S. Xavier UPE
• Cleyton M. de Oliveira Rodrigues UPE

DOI: https://doi.org/10.5753/eniac.2025.13843

Resumo

This study presents the main observations on the use of Machine Learning algorithms to predict specific types of violence against women in the state of Pernambuco. Only in 2024, more than 30.000 cases of gender-based violence were reported, with more than 100 resulting in homicide, in addition to serious harm to women’s health. Therefore, the objective of the study is to find the best models for predicting specific types of violence to mitigate future cases. To this end, data from the Ministry of Women from 2015 to 2021 were used, in addition to tests with different Machine Learning models, resulting in models with accuracy and precision above 70% and 75%, respectively. In addition, an interpretability analysis was performed to identify bias in the best model.

Referências

Bafna, P., Pramod, D., and Vaidya, A. (2016). Document clustering: Tf-idf approach. In 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), pages 61–66.

Conselho Nacional de Justiça (2024). Painel violência contra a mulher [violence against women dashboard]. Available at: [link].

da Silva, B. B. (2024). Application of machine learning in the detection and prevention of femicide - a systematic review. DOI: 10.5281/zenodo.10802399.

da Silva, B. B. A., Pereira, R. M., de Oliveira Rodrigues, C. M., and de Araújo Fagundes, R. A. (2024). Analyzing patterns of violence against women in pernambuco using self-organizing maps and apriori algorithm. In 2024 IEEE Latin American Conference on Computational Intelligence (LA-CCI), pages 1–6, Bogotá D.C., Colombia.

de Barros, S. C., da Rocha Pimentel, D., de Oliveira, C. M., and do Bonfim, C. V. (2021). Factors associated with the homicides of women who are victims of violence. Revista Brasileira de Enfermagem, 21(5).

Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., and Gulin, A. (2018). Cat-boost: unbiased boosting with categorical features. In Advances in Neural Information Processing Systems 31 (NeurIPS 2018), pages 6638–6648.

Secretaria de Comunicação Social (2024). Ligue 180 registra aumento de 40 % nos atendimentos em 2024 [ligue 180 registers a 40 % increase in calls in 2024]. Available at: [link].

Singh, K., Mahajan, A., and Mansotra, V. (2021). 1d-cnn based model for classification and analysis of network attacks. International Journal of Advanced Computer Science and Applications (IJACSA), 12(11).