Serviços Personalizados
Journal
Artigo
Indicadores
- Citado por SciELO
- Acessos
Links relacionados
- Citado por Google
- Similares em SciELO
- Similares em Google
Compartilhar
Revista Facultad de Ingeniería
versão impressa ISSN 0121-1129versão On-line ISSN 2357-5328
Resumo
PINTO-MUNOZ, Cristian-Camilo; ZUNIGA-SAMBONI, Jhon-Alex e ORDONEZ-ERAZO, Hugo-Armando. Machine Learning Applied to Gender Violence: A Systematic Mapping Study. Rev. Fac. ing. [online]. 2023, vol.32, n.64, 5. Epub 27-Ago-2023. ISSN 0121-1129. https://doi.org/10.19053/01211129.v32.n64.2023.15944.
Machine Learning (ML) has positioned itself as one of the best tools to address different problems thanks to its data processing capabilities, as well as the different models, algorithms, and predictive factors that help to solve defined problems. Therefore, this article presents a systematic mapping from 2018 to 2023 focused on the application of ML to gender-based violence. The methodology followed for this study is based on the definition of elements such as research questions, search strings, bibliographic sources, and inclusion and exclusion criteria. The research results allow us to understand the benefits and challenges of using artificial intelligence, precisely one of its branches, ML, to help combat problems in different areas of society, such as education, health, and violence, among others. It also identifies the countries where ML is being researched and the contexts it is applied to. The study discusses the application of ML to combat gender-based violence. After conducting a literature review, beneficial results were found in the application of artificial intelligence and ML. The results obtained in the different articles showed a predictive capacity and improvements compared to currently used systems. However, despite the positive results, no evidence of the development of an ML model or algorithm applied to gender-based violence in Colombia was found in the review.
Palavras-chave : domestic violence; gender-based violence; machine learning; prediction.