Towards Real-World Rumor Detection: Anomaly Detection Framework with Graph Supervised Contrastive Learning
This work addresses rumor detection for social media platforms, offering an incremental improvement by adapting existing methods to handle real-world data imbalances.
The paper tackles rumor detection in social media by addressing data scarcity and imbalance, proposing an anomaly detection framework with graph supervised contrastive learning that shows superiority in balanced, imbalanced, and few-shot conditions.
Current rumor detection methods based on propagation structure learning predominately treat rumor detection as a class-balanced classification task on limited labeled data. However, real-world social media data exhibits an imbalanced distribution with a minority of rumors among massive regular posts. To address the data scarcity and imbalance issues, we construct two large-scale conversation datasets from Weibo and Twitter and analyze the domain distributions. We find obvious differences between rumor and non-rumor distributions, with non-rumors mostly in entertainment domains while rumors concentrate in news, indicating the conformity of rumor detection to an anomaly detection paradigm. Correspondingly, we propose the Anomaly Detection framework with Graph Supervised Contrastive Learning (AD-GSCL). It heuristically treats unlabeled data as non-rumors and adapts graph contrastive learning for rumor detection. Extensive experiments demonstrate AD-GSCL's superiority under class-balanced, imbalanced, and few-shot conditions. Our findings provide valuable insights for real-world rumor detection featuring imbalanced data distributions.