Leveraging Relationships in Social Networks for Sentiment Analysis

Resumo

The emergence of online social networks in the past few years has generated an enormous amount of valuable data containing user opinions and experiences about the most varied subjects. Aiming to identify the orientation of user postings, several sentiment analysis techniques have been proposed - mainly based on text analysis. We propose here a different perspective to treat this problem, based on a user centric approach. We adopt a graph representation in which nodes represent users and connections represent their relationships in social networks. When available, the user opinion orientation is used to tag the user node. Then, we apply link mining techniques to infer opinions of users who have not posted their opinion about the subject under analysis. Preliminary experiments on a Twitter corpus of political preferences have shown promising results.