Grouping Like-Minded Users Based on Text and Sentiment Analysis Soufiene Jaffali, Salma Jamoussi, and Abdelmajid Ben Hamadou MIRACL Laboratory Higher Institute of Computer Science and Multimedia, Sfax, BP 1030 - Tunisia. University of Sfax. Abstract. With the growth of social media usage, the study of online communities and groups has become an appealing research domain. In this context, grouping like-minded users is one of the emerging problems. Indeed, it gives a good idea about group formation and evolution, ex- plains various social phenomena and leads to many applications, such as link prediction and product suggestion. In this dissertation, we propose a novel unsupervised method for grouping like-minded users within social networks. Such a method detects groups of users sharing the same in- terest centers and having similar opinions. In fact, the proposed method is based on extracting the interest centers and retrieving the polarities from the user’s textual posts. Keywords: Social network, like-minded users, interest center, senti- ment analysis 1 Introduction Building relationships is one of the principal activities in social networks as this allows the interaction between users having something in common (ethnicity, locality, interest center, etc.). Since people are selectively connected to others, the interactions between users leads to social groups (communities). Therefore, identifying and understanding groups of users sharing similar interests are emer- gent tasks of Social Network Analysis (SNA) leading to many applications such as the friend suggestion systems, the collaborative filtering, etc. Most of the works concerned with this issue deals with it as a graph-distribution problem, in which the users are represented by nodes and the relationships between them by edges [22]. These relationships are generally explicit friendship links (”friend” on Facebook, ”follower/followee” on Twitter, etc.). According to the big tail distribution of social networks [21], most of the social media users have only few links. Therefore, it is hard to find like-minded people who are several steps away from each other within the same social network. In addition, regarding the huge number of social network users (over 645,750,000 active registered Twitter users according to Statistic Brain 1 ), mining only explicit relations within the 1 http://www.statisticbrain.com/twitter-statistics