FROM DATA TO ACTION: GENERATIVE AI FOR TACKLING VIOLENCE AGAINST WOMEN

AN EVIDENCE-INFORMED NATURAL-LANGUAGE ASSISTANT FOR FEMICIDE PREVENTION

Authors

DOI:

https://doi.org/10.66838/sauc.6433

Keywords:

Generative AI; Natural Language Interfaces; Public Safety; Femicide Data; Text-to-SQL; Urban Governance; Evidence-Informed Policymaking

Abstract

Public data availability does not ensure effective use by policymakers, professionals, or citizens. This study developed and validated a Generative AI assistant providing natural-language access to femicide data in Mato Grosso do Sul, Brazil. Evaluated with institutional data in a TRL-5-consistent environment, the system generates read-only SQL against a curated database. Across 18 benchmark questions, SQL executability, data retrieval, and factual consistency each reached 94.1%, with 100% source attribution and 83.3% safe behavior. Thirty-six supplementary interactions broadened geographic and query-formulation coverage, while all 12 adversarial prompts met expected safety behavior. The assistant offers a promising evidence-access layer for violence-against-women data.

Downloads

Download data is not yet available.

Global Statistics ℹ️

Cumulative totals since publication
99
Views
19
Downloads
118
Total

References

Alcantara, P. P. T. de, Carneiro, F. F., Pessoa, V. M., Pinto, A. G. A., & Machado, M. de F. A. S. (2024). Comprehensive care for women victims of violence. Ciência & Saúde Coletiva, 29 (9), e08992023. https://doi.org/10.1590/1413-81232024299.08992023 DOI: https://doi.org/10.1590/1413-81232024299.08992023en

Carmona-Martínez, A., Jara, A., & Molina, G. (2025). SLMs for natural language database interaction with the SENSE Citiverse of Cartagena City. Street Art & Urban Creativity, 11(7), 137–157. https://doi.org/10.62161/sauc.v11.6023 DOI: https://doi.org/10.62161/sauc.v11.6023

European Innovation Council. (2020). Programme finder (1/3): Understanding Technology Readiness Level (TRL). European Commission. Retrieved September 13, 2026, from https://eic.ec.europa.eu/programme-finder-13_en

Fórum Brasileiro de Segurança Pública. (2024). 18º Anuário Brasileiro de Segurança Pública. https://publicacoes.forumseguranca.org.br/handle/123456789/253

InnovateUS. (2026, March 17). Using AI to make open data useful: Lessons from the City of Boston [Online workshop]. https://innovate-us.org/leveraging-ai-to-use-open-data-a-city-of-boston-case/

Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023). Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12), Article 248, 1–38. https://doi.org/10.1145/3571730 DOI: https://doi.org/10.1145/3571730

Mendoza, B., Aronson, M., Johnson, H., Levy, S., & Rahman, M. A. (2026). Improving LLM access to federal open data: A pilot study of Model Context Protocol servers for federal data access. U.S. General Services Administration. https://www.ncbi.nlm.nih.gov/books/NBK623584/

Ministério das Mulheres. (2026). RASEAM 2026: Relatório anual socioeconômico da mulher. https://www.gov.br/mulheres/pt-br/central-de-conteudos/publicacoes-1/raseam-2026-relatorio-anual-socioeconomico-da-mulher.pdf

OECD. (2020). Building capacity for evidence-informed policy-making: Lessons from country experiences. OECD Publishing. https://doi.org/10.1787/86331250-en DOI: https://doi.org/10.1787/86331250-en

Russell, S. J., & Norvig, P. (2022). Inteligência artificial: Uma abordagem moderna (D. Vieira & F. S. C. da Silva, Trans.; 4th ed.). GEN LTC. (Original work published 2021)

Schiavo, F., & Freitas de Magalhães, C. (2025). Citizen-centered generative AI for urban transformation: The AI Copacabana demo case. Street Art & Urban Creativity, 11(7), 113–136. https://doi.org/10.62161/sauc.v11.5995 DOI: https://doi.org/10.62161/sauc.v11.5995

Shi, L., Tang, Z., Zhang, N., Zhang, X., & Yang, Z. (2025). A survey on employing large language models for Text-to-SQL tasks. ACM Computing Surveys, 58(2), Article 54, 1–37. https://doi.org/10.1145/3737873 DOI: https://doi.org/10.1145/3737873

United Nations Office on Drugs and Crime, & UN Women. (2025). Femicides in 2024: Global estimates of intimate partner/family member femicides. United Nations. https://www.unodc.org/documents/data-and-analysis/briefs/Femicide_Brief_2025.pdf

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (Vol. 30, pp. 5998–6008). Curran Associates, Inc. https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html

Williams, S., Beery, S., Conley, C., Evans, M. L., Garces, S., Gordon, E., Jacob, N., & Medina, E. (2024). People-powered Gen AI: Collaborating with generative AI for civic engagement. An MIT Exploration of Generative AI. https://doi.org/10.21428/e4baedd9.f78710e6 DOI: https://doi.org/10.21428/e4baedd9.f78710e6

World Health Organization. (2025). RESPECT women: Preventing violence against women (2nd ed.). https://www.who.int/publications/i/item/9789240117020

Yigitcanlar, T., David, A., Li, W., Fookes, C., Bibri, S. E., & Ye, X. (2024). Unlocking artificial intelligence adoption in local governments: Best practice lessons from real-world implementations. Smart Cities, 7(4), 1576–1625. https://doi.org/10.3390/smartcities7040064 DOI: https://doi.org/10.3390/smartcities7040064

Zhang, D., Pee, L. G., Pan, S. L., & Cui, L. (2022). Big data analytics, resource orchestration, and digital sustainability: A case study of smart city development. Government Information Quarterly, 39(1), 101626. https://doi.org/10.1016/j.giq.2021.101626 DOI: https://doi.org/10.1016/j.giq.2021.101626

Downloads

Published

2026-10-05

How to Cite

do Amaral Ruiz, O. G., Rodrigues Lima Caires, A., Ledesma de Nadai, R. D., & Leite de Oliveira, S. (2026). FROM DATA TO ACTION: GENERATIVE AI FOR TACKLING VIOLENCE AGAINST WOMEN: AN EVIDENCE-INFORMED NATURAL-LANGUAGE ASSISTANT FOR FEMICIDE PREVENTION . Street Art & Urban Creativity, 12(5), 623–642. https://doi.org/10.66838/sauc.6433

Issue

Vol. 12 No. 5 (2026)

Section

Research articles

License

Copyright (c) 2026 Authors retain copyright and transfer to the journal the right of first publication and publishing rights

Creative Commons License

This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.

Those authors who publish in this journal accept the following terms:

  1. Authors retain copyright.

  2. Authors transfer to the journal the right of first publication. The journal also owns the publishing rights.

  3. All published contents are governed by an Attribution-NoDerivatives 4.0 International License.
    Access the informative version and legal text of the license. By virtue of this, third parties are allowed to use what is published as long as they mention the authorship of the work and the first publication in this journal. If you transform the material, you may not distribute the modified work.

  4. Authors may make other independent and additional contractual arrangements for non-exclusive distribution of the version of the article published in this journal (e.g., inclusion in an institutional repository or publication in a book) as long as they clearly indicate that the work was first published in this journal.

  5. Authors are allowed and recommended to publish their work on the Internet (for example on institutional and personal websites), following the publication of, and referencing the journal, as this could lead to constructive exchanges and a more extensive and quick circulation of published works (see The Effect of Open Access).