Heterogeneous Subgraph Transformer for Fake News Detection

TL;DR

This paper introduces HeteroSGT, a novel transformer-based method that leverages heterogeneous graph structures and textual semantics to improve fake news detection accuracy on social media.

Contribution

It proposes a heterogeneous subgraph transformer that effectively captures complex relations in news data, enhancing fake news detection beyond existing methods.

Findings

HeteroSGT outperforms five baseline models on five datasets.

The use of subgraph extraction improves detection accuracy.

Ablation studies confirm the effectiveness of the proposed components.

Abstract

Fake news is pervasive on social media, inflicting substantial harm on public discourse and societal well-being. We investigate the explicit structural information and textual features of news pieces by constructing a heterogeneous graph concerning the relations among news topics, entities, and content. Through our study, we reveal that fake news can be effectively detected in terms of the atypical heterogeneous subgraphs centered on them, which encapsulate the essential semantics and intricate relations between news elements. However, suffering from the heterogeneity, exploring such heterogeneous subgraphs remains an open problem. To bridge the gap, this work proposes a heterogeneous subgraph transformer (HeteroSGT) to exploit subgraphs in our constructed heterogeneous graph. In HeteroSGT, we first employ a pre-trained language model to derive both word-level and sentence-level semantics. Then the random walk with restart (RWR) is applied to extract subgraphs centered on each news, which are further fed to our proposed subgraph Transformer to quantify the authenticity. Extensive experiments on five real-world datasets demonstrate the superior performance of HeteroSGT over five baselines. Further case and ablation studies validate our motivation and demonstrate that performance improvement stems from our specially designed components.