Identification of Misogynistic Accounts on Twitter Through Graph Convolutional Networks

Misogyny refers to the deeply ingrained bias against women, characterised by feelings of hatred, aversion, and distrust primarily due to their gender. With a large dataset of Italian-written tweets, our research aims to analyse the individuals who generate and disseminate misogynistic information. To achieve this, we first use a Graph Convolutional Network approach to categorise Twitter accounts into a binary misogyny scheme, leveraging both textual and relational data from friend/follower relationships. Then, we compare the retrieved misogynistic and non-misogynistic communities, considering both network centrality measures and linguistic features.