A unified framework for multi-modal rumor detection via multi-level dynamic interaction with evolving stances

Tiening Sun, Chengwei Liu, Lizhi Chen, Zhong Qian, Peifeng Li, Qiaoming Zhu

Abstract: Highlights•Capturing temporal evolution of rumors through snapshots at different stages.•Generating user stances using ChatGPT to understand cognitive shifts in conversations.•Designing multi-level fusion for enhanced representations of graphs and multi-modal data.•Aligning dynamic conversation graphs using contrastive learning for enhanced classification.