Hy-DeFake: Hypergraph Neural Networks for Detecting Fake News in Online Social Networks

TL;DR

Hy-DeFake introduces a hypergraph neural network approach that models high-order relations in social networks to improve fake news detection, especially when textual auxiliary information is scarce.

Contribution

The paper proposes a hypergraph neural network method that captures complex relations in social networks for more effective fake news detection, addressing limitations of previous simple graph-based methods.

Findings

Hy-DeFake outperforms eight baseline methods across four datasets.

The method effectively captures high-order relations and semantic content.

It demonstrates robustness even with limited textual auxiliary information.

Abstract

Nowadays social media is the primary platform for people to obtain news and share information. Combating online fake news has become an urgent task to reduce the damage it causes to society. Existing methods typically improve their fake news detection performances by utilizing textual auxiliary information (such as relevant retweets and comments) or simple structural information (i.e., graph construction). However, these methods face two challenges. First, an increasing number of users tend to directly forward the source news without adding comments, resulting in a lack of textual auxiliary information. Second, simple graphs are unable to extract complex relations beyond pairwise association in a social context. Given that real-world social networks are intricate and involve high-order relations, we argue that exploring beyond pairwise relations between news and users is crucial for fake news detection. Therefore, we propose constructing an attributed hypergraph to represent non-textual and high-order relations for user participation in news spreading. We also introduce a hypergraph neural network-based method called Hy-DeFake to tackle the challenges. Our proposed method captures semantic information from news content, credibility information from involved users, and high-order correlations between news and users to learn distinctive embeddings for fake news detection. The superiority of Hy-DeFake is demonstrated through experiments conducted on four widely-used datasets, and it is compared against eight baselines using four evaluation metrics.