Extracting Graph Topological Information and Users’ Opinion

This paper focuses on the role of social relations within social media in the formation of public opinion. We propose to combine the detection of the users’ stance towards BREXIT, carried out by content analysis of Twitter messages, and the exploration of their social relations, by relying on social network analysis. The analysis of a novel Twitter corpus on the BREXIT debate, developed for our purposes, shows that like-minded individuals (sharing the same opinion towards the specific issue) are likely belonging to the same social network community. Moreover, opinion driven homophily is exhibited among neighbours. Interestingly, users’ stance shows diachronic evolution.