Early Signals of Trending Rumor Event in Streaming Social Media

Abstract

In this study, we propose a mechanism for identifying early signals of trending rumor events (i.e. controversial emerging topics) in streaming social media. The pattern, combining features of both user's attitude and information diffusion, is applied in the sliding windows of social media data streams. By capturing and analyzing frequent patterns within early windows, we found signal patterns appearing at very early stages of trending rumor events (in average, months before their peak time). Our preliminary empirical analysis is applied in two different Twitter datasets. The obtained results indicate the potential of our approach to detect trending rumor event candidates (with high probability of being false) as early as possible in real-time environments.