Spatio-Temporal Disinformation Detection Using GNN–LSTM and Cross-Attention for South China Sea Information Analysis
##plugins.themes.bootstrap3.article.main##
Abstract
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.
##plugins.themes.bootstrap3.article.details##
[2] C. Ivan, I. Chiru, and R. Arcos, “A whole of society intelligence approach: critical reassessment of the tools and means used to counter information warfare in the digital age,” Intell. Natl. Secur., vol. 36, no. 4, pp. 495–511, 2021, doi: https://doi.org/10.1080/02684527.2021.1893072.
[3] B. Huang, “Navigating digital divide: exploring the influence of ideological and political education on cyber security and digital literacy amid information warfare,” Curr. Psychol., vol. 43, no. 28, pp. 23815–23836, 2024, doi: https://doi.org/10.1007/s12144-024-06106-1.
[4] R. Arcos and H. Smith, “Digital communication and hybrid threats,” Rev. ICONO 14. Rev. científica Comun. y Tecnol. emergentes, vol. 19, no. 1, pp. 1–14, 2021, doi: https://doi.org/10.7195/ri14.v19i1.1662.
[5] S. Vosoughi, D. Roy, and S. Aral, “The spread of true and false news online,” Science (80-. )., vol. 359, no. 6380, pp. 1146–1151, 2018, doi: 10.1126/science.aap9559.
[6] Z. Jin, J. Cao, Y. Zhang, and J. Luo, “News verification by exploiting conflicting social viewpoints in microblogs,” in Proceedings of the AAAI conference on artificial intelligence, 2016, vol. 30, no. 1. doi: https://doi.org/10.1609/aaai.v30i1.10382.
[7] D. I. Sukmawan and R. Pedrason, “Assertively Hedging? Indonesia’s Motives and Practices in the South China Sea,” Intermestic J. Int. Stud., vol. 7, no. 2, pp. 701–720, 2023.
[8] C. Paul and M. Matthews, “The Russian ‘firehose of falsehood’ propaganda model,” Rand Corp., vol. 2, no. 7, pp. 1–10, 2016.
[9] C. Paul and M. Matthews, “Defending against Russian propaganda,” SAGE Handb. Propag., pp. 286–302, 2020.
[10] H. R. Saeidnia, E. Hosseini, B. Lund, M. A. Tehrani, S. Zaker, and S. Molaei, “Artificial intelligence in the battle against disinformation and misinformation: a systematic review of challenges and approaches,” Knowl. Inf. Syst., vol. 67, no. 4, pp. 3139–3158, 2025, doi: https://doi.org/10.1007/s10115-024-02337-7.
[11] M. R. Islam, S. Liu, X. Wang, and G. Xu, “Deep learning for misinformation detection on online social networks: a survey and new perspectives,” Soc. Netw. Anal. Min., vol. 10, no. 1, p. 82, 2020, doi: 10.1007/s13278-020-00696-x.
[12] K. Alahmadi, S. Alharbi, J. Chen, and X. Wang, “Generalizing sentiment analysis: a review of progress, challenges, and emerging directions,” Soc. Netw. Anal. Min., vol. 15, no. 1, p. 45, 2025, doi: https://doi.org/10.1007/s13278-025-01461-8.
[13] P. Lops, D. Jannach, C. Musto, T. Bogers, and M. Koolen, “Trends in content-based recommendation: Preface to the special issue on Recommender systems based on rich item descriptions,” User Model. User-adapt. Interact., vol. 29, no. 2, pp. 239–249, 2019, doi: https://doi.org/10.1007/s11257-019-09231-w.
[14] D. Nath and S. K. Dwivedi, “Aspect-based sentiment analysis: approaches, applications, challenges and trends,” Knowl. Inf. Syst., vol. 66, no. 12, pp. 7261–7303, 2024, doi: https://doi.org/10.1007/s41060-017-0082-x.
[15] B. Khemani, S. Patil, K. Kotecha, and S. Tanwar, “A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions,” J. Big Data, vol. 11, no. 1, p. 18, 2024, doi: 10.1186/s40537-023-00876-4.
[16] V. Ponzi and C. Napoli, “Graph Neural Networks: Architectures, Applications, and Future Directions,” IEEE Access, vol. 13, pp. 62870–62891, 2025, doi: 10.1109/ACCESS.2025.3558752.
[17] H. Rama Moorthy et al., “Dual stream graph augmented transformer model integrating BERT and GNNs for context aware fake news detection,” Sci. Rep., vol. 15, no. 1, p. 25436, 2025.
[18] L. Selvam, E. S. Vinothkumar, R. S. Krishnan, G. V. Rajkumar, J. R. F. Raj, and P. S. R. Malar, “A Unified Deep Learning Model for Fake Account Identification Using Transformer-Based NLP and Graph Neural Networks,” in 2025 International Conference on Inventive Computation Technologies (ICICT), 2025, pp. 1033–1040.
[19] B. Lakzaei, M. Haghir Chehreghani, and A. Bagheri, “Disinformation detection using graph neural networks: a survey,” Artif. Intell. Rev., vol. 57, no. 3, p. 52, 2024.
[20] S. Kuntur et al., “Graph Neural Networks for Misinformation Detection: Performance-Efficiency Trade-offs,” arXiv Prepr. arXiv2604.08131, 2026.
[21] P. Gupta and P. K. Gupta, “Performance analysis of gcn, gnn, and gat models with differentiable pooling for detection of fake news,” in 2024 3rd Edition of IEEE Delhi Section Flagship Conference (DELCON), 2024, pp. 1–6.
[22] A. Sankar, Y. Wu, L. Gou, W. Zhang, and H. Yang, “DySAT : Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks,” pp. 519–527, 2020, doi: https://doi.org/10.1145/3336191.3371845.
[23] A. Pareja et al., “EvolveGCN : Evolving Graph Convolutional Networks for Dynamic Graphs,” 2018, doi: https://doi.org/10.1609/aaai.v34i04.5984.
[24] Y. Zhong and C. Huang, “A dynamic graph representation learning based on temporal graph transformer,” Alexandria Eng. J., vol. 63, pp. 359–369, 2023, doi: https://doi.org/10.1016/j.aej.2022.08.010.
[25] M. Krichen and A. Mihoub, “Long short-term memory networks: A comprehensive survey,” AI, vol. 6, no. 9, p. 215, 2025, doi: https://doi.org/10.3390/ai6090215.
[26] M. Rithani, R. P. Kumar, and S. Doss, “A review on big data based on deep neural network approaches,” Artif. Intell. Rev., vol. 56, no. 12, pp. 14765–14801, 2023, doi: https://doi.org/10.1007/s10462-023-10512-5.
[27] J. Manurung, P. Sihombing, M. A. Budiman, and Sawaluddin, “Dynamic Rumor Control in Social Networks Using Temporal Graph Neural Networks,” in 2023 IEEE International Conference of Computer Science and Information Technology: The Role of Artificial Intelligence Technology in Human and Computer Interactions in the Industrial Era 5.0, ICOSNIKOM 2023, 2023, pp. 1–5. doi: 10.1109/ICoSNIKOM60230.2023.10364382.
[28] J. Wang, X. Wang, and A. Yu, “Tackling misinformation in mobile social networks a BERT-LSTM approach for enhancing digital literacy,” Sci. Rep., vol. 15, no. 1, p. 1118, 2025, doi: https://doi.org/10.1038/s41598-025-85308-4.
[29] L. Abualigah, Y. Y. Al-Ajlouni, M. S. Daoud, M. Altalhi, and H. Migdady, “Fake news detection using recurrent neural network based on bidirectional LSTM and GloVe,” Soc. Netw. Anal. Min., vol. 14, no. 1, p. 40, 2024, doi: https://doi.org/10.1007/s13278-024-01198-w.
[30] G. Loukides and R. Gwadera, “Preventing the diffusion of information to vulnerable users while preserving pagerank,” Int. J. Data Sci. Anal., vol. 5, no. 1, pp. 19–39, 2018, doi: https://doi.org/10.1007/s41060-017-0082-x.
[31] J.-X. Xia, W.-W. Jia, P. Li, and X.-K. Xu, “MSTD: A Joint Structural–Temporal Framework for Fake News Detection,” IEEE Trans. Comput. Soc. Syst., 2026, doi: 0.1109/TCSS.2026.3674080.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.