TSNN: A Topic and Structure Aware Neural Network for Rumor Detection

Abstract

Detecting rumors on social media and preventing its spread play a critical role for politics, economy, etc. Conventional studies mainly focus on exploiting the content or context of the source post, while they always ignore the rich topic information within the source post. To tackle this issue, in this paper, we propose a Topic and Structure Aware Neural Network (TSNN) for rumor detection. To be specific, we explore two kinds of topic signals, including a coarse-grained topic signal (i.e., topic credibility) and a fine-grained topic signal (i.e., latent topic representation), and tailor them to the task of rumor detection. Moreover, we introduce a new auxiliary task, i.e., topic credibility prediction, in order to effectively leverage the rich topic information within source posts. Finally, we develop a multi-task learning strategy that helps improve rumor detection performance by jointly learning the task of topic credibility prediction and user credibility prediction. Extensive experiments on three real-world datasets demonstrate that the proposed approach TSNN is superior to the state-of-the-art baseline methods.