Heterogeneous Graph Attention Networks for Early Detection of Rumors on Twitter

TL;DR

This paper introduces a novel heterogeneous graph attention network that leverages global semantic relations and propagation structures to improve early rumor detection on Twitter.

Contribution

It proposes a meta-path based heterogeneous graph attention network that effectively captures semantic and structural information for rumor detection.

Findings

Outperforms existing methods on real-world Twitter data

Effective in early-stage rumor detection

Utilizes global semantic relations and propagation structures

Abstract

With the rapid development of mobile Internet technology and the widespread use of mobile devices, it becomes much easier for people to express their opinions on social media. The openness and convenience of social media platforms provide a free expression for people but also cause new social problems. The widespread of false rumors on social media can bring about the panic of the public and damage personal reputation, which makes rumor automatic detection technology become particularly necessary. The majority of existing methods for rumor detection focus on mining effective features from text contents, user profiles, and patterns of propagation. Nevertheless, these methods do not take full advantage of global semantic relations of the text contents, which characterize the semantic commonality of rumors as a key factor for detecting rumors. In this paper, we construct a tweet-word-user heterogeneous graph based on the text contents and the source tweet propagations of rumors. A meta-path based heterogeneous graph attention network framework is proposed to capture the global semantic relations of text contents, together with the global structure information of source tweet propagations for rumor detection. Experiments on real-world Twitter data demonstrate the superiority of the proposed approach, which also has a comparable ability to detect rumors at a very early stage.