Towards Real-World Rumor Detection: Anomaly Detection Framework with Graph Supervised Contrastive Learning

TL;DR

This paper introduces AD-GSCL, an anomaly detection framework using graph contrastive learning for rumor detection, effectively handling imbalanced and limited labeled social media data.

Contribution

It proposes a novel anomaly detection approach with graph supervised contrastive learning tailored for real-world rumor detection.

Findings

AD-GSCL outperforms existing methods in various data imbalance scenarios.

Large-scale datasets from Weibo and Twitter validate the framework's effectiveness.

Rumor and non-rumor distributions differ significantly across domains.

Abstract

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.