Social Indicators from News-Based Gender Violence Events

• Samuel R. S. Oliveira Universidade de São Paulo (USP)
• Daniel Zitei Universidade de São Paulo (USP)
• Ricardo M. Marcacini Universidade de São Paulo (USP) https://orcid.org/0000-0002-2309-3487

DOI: https://doi.org/10.5753/sbbd_estendido.2026.249697

Resumo

Official indicators are essential for monitoring gender violence, but they often arrive late and provide limited contextual detail about specific events. This paper explores online news as a complementary social sensing layer for producing low-latency indicators of gender violence. We propose a pipeline that collects news reports, retrieves target-related documents, removes duplicates, normalizes temporal and geographic information, and uses language models to classify gender violence events and extract structured metadata. Each event includes attributes such as violence type, location, victim–aggressor relationship, severity, outcome, and event dynamics. Using Brazilian news from 2020 to April 2026 as a case study, we show how structured news-based events can support temporal monitoring, spatial analysis, comparison with official data, and executive summaries of emerging peaks. The results indicate that news can anticipate signals, enrich interpretation, and support public managers with more timely and semantically detailed evidence.

Palavras-chave: news-based social indicators, text mining, machine learning

Referências

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.

FBSA (2025). 19º anuário brasileiro de segurança pública. [link]. Accessed: 2026-05-26.

Ginsberg, J., Mohebbi, M. H., Patel, R. S., Brammer, L., Smolinski, M. S., and Brilliant, L. (2009). Detecting influenza epidemics using search engine query data. Nature, 457(7232):1012–1014.

Gôlo, M. P. S., Rossi, R. G., and Marcacini, R. M. (2021). Learning to sense from events via semantic variational autoencoder. PLOS ONE, 16(12):e0260701.

IPEA (2025). Atlas da violência 2025. [link]. Accessed: 2026-05-26.

Leetaru, K. and Schrodt, P. A. (2013). Gdelt: Global data on events, location, and tone, 1979–2012. In ISA Annual Convention.

Marcacini, R. M., Rossi, R. G., Nogueira, B. M., Martins, L. V., Cherman, E. A., and Rezende, S. O. (2017). Websensors analytics: Learning to sense the real world using web news events. In XXIII Brazilian Symposium on Multimedia and the Web: Workshops and Posters, pages 169–173.

ReVeJo (2025). Repositório de veículos jornalísticos. [link]. Accessed: 2026-05-26.

Sakaki, T., Okazaki, M., and Matsuo, Y. (2010). Earthquake shakes twitter users: real-time event detection by social sensors. In Proceedings of the 19th International Conference on World Wide Web, pages 851–860.

Senado Federal (2024). Mapa nacional da violência de gênero. [link]. Accessed: 2026-05-26.

Vasconcelos, N. M. d., Bernal, R. T. I., Souza, J. B. d., Bordoni, P. H. C., Stein, C., and Coll (2024). Underreporting of violence against women: an analysis of two data sources. Ciência & Saúde Coletiva, 29(10):e07732023.

Wei, C.-P. and Lee, Y.-H. (2004). Event detection from online news documents for supporting environmental scanning. Decision Support Systems, 36(4):385–401.

WHO 2024 (2024). Violence against women. [link]. Accessed: 2026-05-26.