A novel approach for rumor detection in social platforms: Memory-augmented transformer with graph convolutional networks

Qian Chang, Xia Li, Zhao Duan

Abstract: Highlights•Our study presents a novel approach, combining memory-augmented transformer with graph convolution networks (GCNs), for effective rumor detection in social platforms.•The memory-augmented transformer enables our model to capture both local and global dependencies in rumor propagation, enhancing contextual understanding.•GCNs facilitate the integration of intrinsic and extrinsic information sources from structural information, providing a comprehensive view of the information ecosystem for improved detection accuracy.•Rigorous evaluations on real-world chinese and english datasets showcase the advanced capabilities of our GCNs-MT model in identifying and combating misinformation.•The proposed approach holds practical implications for countering the widespread dissemination of false information in social media platforms, contributing to information integrity and trustworthiness.