Using Social Network Analysis in Understanding The Public Discourse on Gender Violence: an Agent-Based Modelling Approach
There are many representations attributed to gender-based violence. Public discourse provides useful datasets that can be studied in order to study such representations. Social network modelling is a way to study that public discourse, by looking at how opinions in a discourse interact and repeat themselves on a large scale and over time. This study aims to construct a social network model using an agent-based approach to measure whether the conversation space of certain gender violence discourses are more centered on victims, perpetrators, institutions, or society. It will use network measures of centrality, immediate impact analysis, and centrality changes over time to compare the context of two cultures: Philippines and the United States. The data set from the Philippines consists of articles on the Vizconde Massacre and the data set from the United States consists of articles on the Stanford Rape Case. Results show that both datasets feature an institution-centric discourse that is consistent over time, and that society has the lowest role-centrality in both events. Perpetrators appear more central than victims, but comparatively more so in the Stanford Rape dataset compared to the Vizconde Massacre one.
Meliza M. De La Paz and Ma. Regina E. Estuar. 2017. Using Social Network Analysis in Understanding The Public Discourse on Gender Violence: an Agent-Based Modelling Approach. In Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017 (ASONAM ’17). Association for Computing Machinery, New York, NY, USA, 1144–1151. DOI:https://doi.org/10.1145/3110025.3120960