Differentiating users by language and location estimation in sentiment analisys of informal text during major public events

In recent years there has been intense work on the analysis of social media to support marketing campaigns. A proper methodology for sentiment analysis is a crucial asset in this regard. However, when monitoring major public events the behaviour or social media users may be strongly biased by punctual actions of the participating characters and the sense of group belonging, which is typically linked to specific geographical areas. In this paper, we present a solution combining a location prediction methodology with an unsupervised technique for sentiment analysis to assess automatically the engagement of social network users in different countries during an event with worldwide impact. As far as the authors know, this is the first time such techniques are jointly considered. We demonstrate that the technique is coherent with the intrinsic disposition of individual users to typical actions of the characters participating in the events, as well as with the sense of group belonging.