A feature based approach on behavior analysis of the users on twitter: A case study of AusOpen tennis championship

Abstract

[EN] Due to the advancement of technology, and the promotion of smart- phones, using social media got more and more popular. Nowadays, it has become

an undeniable part of people’s lives. So, they will create a flow of information by the content they share every single moment. Analyzing this information helps us to have a better understanding of users, their needs, their tendencies and classify them into different groups based on their behavior. These behaviors are various and due to some extracted features, it is possible to categorize the users into different categories. In this paper, we are going to focus on Twitter users and the AusOpen Tennis championship event as a case study. We define the attributions describing each class and then extract data and identify features that are more correlated to each type of user and then label user type based on the reasoning model. The results contain 4 groups of users; Verified accounts, Influencers, Regular profiles, and Fake profiles.