A Retweet Network Analysis of the European Parliament

Social media analytics is increasingly used to uncover underlying real-world phenomena. The goal of this paper is to evaluate the role of Twitter in identifying communities of influence when the "ground truth" is known. We consider the European Parliament (EP) Twitter users during a period of eight months, in which they posted over 370,000 tweets. We define influence as a retweet relation between two Twitter users. We construct two networks of influence: (i) core, where both users are EP members, and (ii) extended, where one user can be outside the EP. We detect communities in both networks and compare them to the "ground truth": the political group and country of the EP members. The results show that the core network closely matches the political orientation, while the extended network reflects the country of origin. This provides empirical evidence that the formation of retweet networks and community detection are appropriate tools to reveal the actual relationships, and can therefore be used to uncover hidden properties when the "ground truth" is not known.