TGCN-HCA: temporal graph convolution networks with hierarchical co-attention mechanisms for fake news detection

Semantic-Aware Heterogeneous Graph Learning for Fake News Detection.

Experimental results on real-world datasets demonstrate that SHEAR significantly outperforms existing methods in fake news detection, showcasing the benefits of incorporating behavioral semantic patterns with network motifs for enhanced classification performance.

Diffusion-Induced Spatial Attention Overlapping Community Detection

Diffusion-Induced Spatial Attention Community Detection (DISCO), a deep-learning framework that combines a structural prior derived from influence spreading dynamics, sparse multi-head attention, and non-negative community-affiliation learning, is introduced.

4HAN: An Enhanced Neural Network for Fake News Detection using Hypergraph

A Four-Level Hierarchical Attention Network (4HAN) that incorporates word-, sentence-, and headline-level attention, along with Hypergraph Convolution and Hypergraph Attention, is proposed using the LIAR dataset and shows a detection accuracy rate of 96.00%, which beats multiple existing methodologies in fake news dete...

Evidence-aware fake news detection with graph neural networks via prompt-guided semantic structuring and dynamic evidence selection

Temporal heterogeneous graph neural networks for multimodal rumor detection on social media

THGNN-MRD, a temporal heterogeneous graph neural network for multimodal rumor detection, is proposed, suggesting that modeling rumors as evolving multimodal social events provides a principled and effective solution for trustworthy rumor detection.

Multimodal Fusion Model for Fake News Detection Combining BERT and Graph Attention Networks

This work proposes a framework that combines BERT text embeddings with Graph Attention Network representations of propagation graphs that combines BERT text embeddings with Graph Attention Network (GAT) representations of propagation graphs.