Machine Learning to study the impact of gender-based violence in the news media

TL;DR

This paper employs machine learning to analyze how news media coverage influences public awareness and perceptions of gender-based violence, revealing thematic and case-related effects.

Contribution

It introduces a neural network-based approach to quantify media impact on GBV awareness and can be adapted to other topics or media sources.

Findings

Relationship between GBV news and public awareness

Effect of mediatic GBV cases on perception

Intrinsic thematic connections in GBV news

Abstract

While it remains a taboo topic, gender-based violence (GBV) undermines the health, dignity, security and autonomy of its victims. Many factors have been studied to generate or maintain this kind of violence, however, the influence of the media is still uncertain. Here, we use Machine Learning tools to extrapolate the effect of the news in GBV. By feeding neural networks with news, the topic information associated with each article can be recovered. Our findings show a relationship between GBV news and public awareness, the effect of mediatic GBV cases, and the intrinsic thematic relationship of GBV news. Because the used neural model can be easily adjusted, this also allows us to extend our approach to other media sources or topics