Region-enhanced Deep Graph Convolutional Networks for Rumor Detection
This work addresses the problem of detecting rumors in social media data, which is crucial for mitigating misinformation spread, but it appears incremental as it builds on existing graph-based methods by adding regional patterns.
The authors tackled rumor detection on social media by proposing a region-enhanced deep graph convolutional network (RDGCN) that learns regionalized propagation patterns, achieving better performance than baselines on Twitter15 and Twitter16 datasets for both rumor detection and early detection.
Social media has been rapidly developing in the public sphere due to its ease of spreading new information, which leads to the circulation of rumors. However, detecting rumors from such a massive amount of information is becoming an increasingly arduous challenge. Previous work generally obtained valuable features from propagation information. It should be noted that most methods only target the propagation structure while ignoring the rumor transmission pattern. This limited focus severely restricts the collection of spread data. To solve this problem, the authors of the present study are motivated to explore the regionalized propagation patterns of rumors. Specifically, a novel region-enhanced deep graph convolutional network (RDGCN) that enhances the propagation features of rumors by learning regionalized propagation patterns and trains to learn the propagation patterns by unsupervised learning is proposed. In addition, a source-enhanced residual graph convolution layer (SRGCL) is designed to improve the graph neural network (GNN) oversmoothness and increase the depth limit of the rumor detection methods-based GNN. Experiments on Twitter15 and Twitter16 show that the proposed model performs better than the baseline approach on rumor detection and early rumor detection.