Abstract
Rumors often yield adverse societal and economic impacts. Therefore, rumor detection has attracted a surge of research interests. Existing methods mainly focus on finding clues from textual contents, which is not quite effective as rumors can be intentionally manipulated. Recent studies have demonstrated that the propagation structure of rumors can significantly improve rumor detection performance. However, propagation-based methods are still limited as the propagation structure is often sparse at an early stage. In this study, we propose Rumor2vec, a novel rumor detection framework with joint text and propagation structure representation learning. First, we present the concept of the union graph to incorporate propagation structures of all tweets to mitigate the sparsity issue. Then, we leverage network embedding to learn representations of nodes in the union graph. Finally, we propose a framework for rumor representation learning and detection. Experimental results on three real-world datasets demonstrate that our proposed framework can achieve better performance than the state-of-the-art approaches. On two Twitter datasets, our method achieves 79.6% and 85.2% accuracies respectively. On the Weibo dataset, our method achieves a 95.1% accuracy. Further experiments on early rumor detection show that our method can identify rumors ahead of other methods by at least 12 h.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have