Analysis of Facebook Users' Relationships Through Sentiment Classification: A Case Study of Italian Politicians

We illustrate a system that analyzes the homepage of a Facebook user or group in order to automatically detect who has discussed what and how it has been discussed. We have focused the analysis on three main actors of Italian politics. The goal is to ?nd people who agree or disagree about given topics with the owner of the Facebook page under analysis. All public posts shared by a user are retrieved by an ad hoc built crawler. Information such as 'posts', 'comments', 'likes', are extracted from the Facebook page. Each post is classi ?ed as belonging to a set of prede ?ned categories and its sentiment is also detected as being positive, negative or neutral. All the comments to that post are therefore analyzed and categorized together with its sentiment polarity. For each Facebook user under analysis a statistics of the topics dealt with is made, and for each category a graph is created where the concordance of sentiment is highlighted between the posts belonging to a given class and the related comments of the people interacting with the user or group under analysis. The graph can therefore be used to pro ?le the user relationships according to sentiment classi ?cation.