RAGAT-Mind: A Multi-Granular Modeling Approach for Rumor Detection Based on MindSpore
Zhenkai Qin, Guifang Yang, Dongze Wu
TL;DR
RAGAT-Mind tackles Chinese rumor detection by integrating multi-granular semantic and structural representations within MindSpore. The model combines TextCNN for local semantics, GRU for sequential context, Multi-Head Self-Attention for global focus, and BiGCN for word co-occurrence structure, evaluated on Weibo1-Rumor with near-perfect accuracy. Results show 99.2% accuracy and Macro-F1 of 0.9919, outperforming baselines while maintaining low latency. The work highlights the benefit of joint semantic-structural representation learning and provides interpretable mechanisms via attention and graph propagation. Potential extensions include cross-domain adaptation and multimodal rumor detection.
Abstract
As false information continues to proliferate across social media platforms, effective rumor detection has emerged as a pressing challenge in natural language processing. This paper proposes RAGAT-Mind, a multi-granular modeling approach for Chinese rumor detection, built upon the MindSpore deep learning framework. The model integrates TextCNN for local semantic extraction, bidirectional GRU for sequential context learning, Multi-Head Self-Attention for global dependency focusing, and Bidirectional Graph Convolutional Networks (BiGCN) for structural representation of word co-occurrence graphs. Experiments on the Weibo1-Rumor dataset demonstrate that RAGAT-Mind achieves superior classification performance, attaining 99.2% accuracy and a macro-F1 score of 0.9919. The results validate the effectiveness of combining hierarchical linguistic features with graph-based semantic structures. Furthermore, the model exhibits strong generalization and interpretability, highlighting its practical value for real-world rumor detection applications.