Leveraging Diversity-Aware Context Attention Networks for Fake News Detection on Social Platforms

Zhikai Chen, Peng Wu, Li Pan

Abstract: In recent years, social platforms have become the main venue for disseminating fake news. Since much fake news is deliberately fabricated by malicious users or generated by adversarial deep learning models, content-only approaches can not detect fake news effectively. Compared to texts, the propagation patterns of fake news are much harder to be forged. Recent work found that the “context” of news, the tree-structured graph representing the propagation relationship of news and Twitter posts, is vital for fake news detection. Some work utilize graph neural networks to learn the representation of news' context graphs, achieving stunning performance. However, these methods still suffer from two problems. Firstly, Twitters posts in the context of news are not equally important for fake news detection. However, most previous works treat them equally. Moreover, the context of news presents diverse structures such as “star-shaped” graphs, with many nodes interacting with a central node, or “line-shaped” graphs, with sparse connections among neighbors. With single-scale graph representation, previous work can not handle diverse structures well. We propose a novel diversity-aware context attention network to cope with these problems. A context attention pooling function is proposed to extract the critical information within the context. It utilizes an attention module to automatically assign a greater weight to those important posts and a smaller weight to helpless posts. Furthermore, jump knowledge, which concatenates the pooling result from multiple network layers, is adopted. It offers the model multi-scale receptive fields and better adapts to diverse structures. Extensive experiments are conducted under various dataset settings, which confirms the superiority of our approaches over state-of-the-art models.