Fake News Detection on News-Oriented Heterogeneous Information Networks through Hierarchical Graph Attention
This addresses the problem of fake news detection for social media and news platforms, offering a method that is less reliant on text and more robust against deliberate masking, though it appears incremental as it builds on existing graph-based approaches.
The authors tackled fake news detection by modeling news articles and related components as a heterogeneous information network and proposed a Hierarchical Graph Attention Network (HGAT) for node representation learning, which outperformed text-based and other network-based models on two real-world datasets.
The viral spread of fake news has caused great social harm, making fake news detection an urgent task. Current fake news detection methods rely heavily on text information by learning the extracted news content or writing style of internal knowledge. However, deliberate rumors can mask writing style, bypassing language models and invalidating simple text-based models. In fact, news articles and other related components (such as news creators and news topics) can be modeled as a heterogeneous information network (HIN for short). In this paper, we propose a novel fake news detection framework, namely Hierarchical Graph Attention Network(HGAT), which uses a novel hierarchical attention mechanism to perform node representation learning in HIN, and then detects fake news by classifying news article nodes. Experiments on two real-world fake news datasets show that HGAT can outperform text-based models and other network-based models. In addition, the experiment proved the expandability and generalizability of our for graph representation learning and other node classification related applications in heterogeneous graphs.