<![CDATA[The rapid propagation of disinformation through social media presents a significant challenge because information diffusion is characterized by complex interactions among users and continuously evolving temporal patterns. Conventional deep-learning and transformer-based approaches primarily focus on textual or sequential representations and may not fully capture the structural and temporal characteristics of information propagation. This study proposes a spatio-temporal framework for disinformation detection that integrates Graph Neural Network (GNN)-based spatial representation, Long Short-Term Memory (LSTM)-based temporal modeling, and an adaptive cross-attention mechanism for spatial–temporal fusion. The GNN is employed to model relational dependencies within social-media interaction networks, while LSTM captures the temporal evolution of graph-based representations. Cross-attention is subsequently introduced to adaptively model the interaction between spatial and temporal representations rather than relying solely on fixed feature concatenation. The proposed framework is evaluated using a social-media dataset associated with the South China Sea and compared with CNN, LSTM, GNN, BERT, and GAT-BERT baselines. Experimental results show that the proposed model achieves 95.84% accuracy, 95.30% precision, 95.60% recall, and 95.45% F1-score, outperforming the strongest baseline, GAT-BERT, by 2.63 percentage points in accuracy and 2.55 percentage points in F1-score. The ablation analysis further demonstrates that integrating LSTM with GNN improves accuracy by 5.32 percentage points, while the subsequent incorporation of cross-attention provides an additional improvement of 3.74 percentage points. These findings indicate that adaptive spatial–temporal fusion contributes beyond the independent use of graph and sequential encoders and provides a potential decision-support approach for analyzing dynamic disinformation propagation in geopolitical social-media environments.]]>
Copyrights © 2026
