Studying the controversy in online crowds’ interactions

Abstract

Detecting controversy in OSN can be very beneficial in understanding the behavior of the online crowds and the dynamics of their interactions, which leads to better understanding of what moves them and how they can be influenced. In this study, we present a hybrid approach that benefits from structural and content-based approaches to detect controversies in Twitter's trending topics. Unlike many previous works, we do not limit ourselves to a certain domain. However, we do focus on social content written in Arabic. To the best of our knowledge, very limited attention has been invested to undertake this approach in studying controversy in general topics in this region of the world. We collect tweets on different trending topics from different domains. We apply several approaches for controversy detection and compare their outcomes to determine which one is the best.