A Graph-Aware Recurrent Fusion Deep Ensemble Architecture for Fake News Detection
DOI:
https://doi.org/10.31185/wjcms.500Keywords:
Fake News Detection, Graph Neural Networks, Recurrent Neural Networks, Node Embedding, Fusion Learning, Social Media AnalyticsAbstract
With the rapid spread of fake news on social media platforms, it has become essential to develop effective detection mechanisms that overcome the limitations of content-only or propagation-only approaches. This study aims to design a unified framework that jointly models textual semantics and diffusion characteristics for improved misinformation detection. To achieve this, we propose GRAFT-FND, a Graph-Aware Recurrent Fusion Deep Ensemble architecture that integrates contextual word embeddings (Word2Vec, BERT, and BERTweet) with recurrent neural networks (RNN/GRU/LSTM/BiLSTM) and graph-based node embedding methods (Node2Vec and DeepWalk) within a fusion-aware learning module. Extensive experiments conducted on the Twitter15 and Twitter16 benchmark datasets using 10-fold cross-validation demonstrate that the proposed framework consistently outperforms baseline and recent state-of-the-art models, with the fusion mechanism and propagation-aware representations contributing significantly to performance improvement. The results indicate that jointly modelling semantic and structural information enhances the ability to capture complex misinformation patterns and improves generalisation across datasets. In conclusion, the proposed framework provides a robust and scalable solution for fake news detection in social media environments. Future work is recommended to investigate adversarial robustness, real-time deployment, and the integration of multimodal data sources.
Downloads
References
[1] G. Chen, C. Du, Y. Yu, H. Hu, H. Duan, and H. Zhu, “A deepfake image detection method based on a multi-graph attention network,” Electronics, vol. 14, no. 3, p. 482, 2025, doi: 10.3390/electronics14030482.
[2] B. Xie, X. Ma, S. Xue, J. Yang, J. Wu, and H. Fan, “Contrastive multi-knowledge graph learning for fake news detection,” IEEE Transactions on Network Science and Engineering, vol. 12, no. 5, pp. 3948–3961, Sept.–Oct. 2025, doi: 10.1109/TNSE.2025.3567296.
[3] H. Lv, W. Yang, F. Wei, J. Peng, and H. Geng, “Dynamic fusion modeling for multimodal fake news detection,” Information Processing & Management, vol. 61, no. 2, p. 103615, 2024.
[4] S. Alsudani, H. Nasrawi, M. Shattawi, and A. Ghazikhani, “Enhancing Spam Detection: A Crow-Optimized FFNN with LSTM for Email Security ”, WJCMS, vol. 3, no. 1, pp. 28–39, Mar. 2024, doi: 10.31185/wjcms.199.
[5] H. T. Phan, “Graph neural network methods for fake news detection: A comprehensive review,” Computers & Security, vol. 135, p. 103324, 2023.
[6] M. Zhang, Y. Li, and S. Wang, “Explainable multilingual and multimodal fake news detection,” Frontiers in Artificial Intelligence, vol. 8, p. 1690616, 2025.
[7] J. Wang and L. Li, “Temporal-aware multimodal networks for misinformation detection,” IEEE Access, vol. 13, pp. 45821–45835, 2025.
[8] E. Papageorgiou, I. Varlamis, and C. Chronis, “Harnessing Large Language Models and Deep Neural Networks for Fake News Detection,” Information, vol. 16, no. 4, art. no. 297, 2025, doi: 10.3390/info16040297.
[9] S. Kuntur, S. V. Paprzycki, and M. Ganzha, “Comparative Analysis of Graph Neural Networks and Transformers for Robust Fake News Detection,” 2024.
[10] T. Zhukabayeva, Z. Ahmad, A. Adamova, N. Karabayev, and A. Abdildayeva, “An edge-computing-based integrated framework for network traffic analysis and intrusion detection to enhance cyber–physical system security in industrial IoT,” Sensors, vol. 25, no. 8, p. 2395, 2025, doi: 10.3390/s25082395.
[11] R. Bharati, J. Bharti, and V. Dehalwar, “A novel fuzzy logic-based hybrid framework for detecting fake news,” Discover Computing, vol. 29, Art. no. 58, 2026, doi: 10.1007/s10791-025-09882-x.
[12] W. Xu and K. Sasahara, “Domain-based user embedding for competing events on social media,” Journal of Computational Social Science, vol. 9, Art. no. 15, 2026, doi: 10.1007/s42001-025-00439-y.
[13] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, Minneapolis, MN, USA, 2019, pp. 4171–4186.
[14] Y. Liu et al., “RoBERTa: A robustly optimized BERT pretraining approach,” in Proc. Int. Conf. Learning Representations (ICLR), 2020.
[15] D. Q. Nguyen, T. Vu, and A. T. Nguyen, “BERTweet: A pre-trained language model for English tweets,” in Proc. EMNLP, 2020, pp. 1727–1737.
[16] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” in Proc. Int. Conf. Learning Representations (ICLR Workshop), 2013.
[17] J. Pennington, R. Socher, and C. D. Manning, “GloVe: Global vectors for word representation,” in Proc. EMNLP, Doha, Qatar, 2014, pp. 1532–1543.
[18] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[19] K. Cho et al., “Learning phrase representations using RNN encoder–decoder for statistical machine translation,” in Proc. EMNLP, Doha, Qatar, 2014, pp. 1724–1734.
[20] AB. M. Merzah, J. Razmara, and Z. Salmanian, “Hybrid Deep Learning Models for Fake News Detection: Case Study on Arabic and English Languages,” Frontiers in Big Data, vol. 8, art. no. 1683786, 2026, doi: 10.3389/fdata.2025.1683786.
[21] W. Cui and M. Shang, “MIGCL: Fake news detection with multimodal interaction and graph contrastive learning networks,” Applied Intelligence, vol. 55, Art. no. 78, 2025, doi: 10.1007/s10489-024-05883-3.
[22] C.-O. Truică, E.-S. Apostol, M. Marogel, and A. Paschke, “GETAE: Graph Information Enhanced Deep Neural Network Ensemble Architecture for Fake News Detection,” Expert Systems with Applications, vol. 275, art. no. 126984, 2025.
[23] S. Wu, Y. Sun, and J. Tang, “Propagation-based rumor detection with graph attention networks,” IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 9, pp. 5642–5655, 2023.
[24] X. Huang, J. Zhou, and H. Wang, “Graph neural network-based misinformation detection on social media,” Pattern Recognition, vol. 138, p. 109384, 2023.
[25] V. S. Nivedita and A. Bazila Banu, “A Hybrid Contrastive Graph Neural Network Framework for Fake News and Hate Speech Detection Using Content and User Interaction Signals,” Scientific Reports, vol. 16, art. no. 669, 2026, doi: 10.1038/s41598-025-30299-5.
[26] J. Rout, M. Mishra, and M. J. Saikia, “Towards reliable fake news detection: Enhanced attention-based transformer model,” Journal of Cybersecurity and Privacy, vol. 5, no. 3, p. 43, 2025, doi: 10.3390/jcp5030043.
[27] Y. Guo, L. Qiao, Z. Yang, J. Xiang, X. Feng, and H. Ma, “Fake news detection: Extendable to global heterogeneous graph attention network with external knowledge,” Tsinghua Science and Technology, vol. 30, no. 3, pp. 1125–1138, Jun. 2025, doi: 10.26599/TST.2023.9010104.
[28] A. Golovin, N. Zhukova, R. Delhibabu, and A. Subbotin, “Improving recommender systems for fake news detection in social networks with knowledge graphs and graph attention networks,” Mathematics, vol. 13, no. 6, p. 1011, 2025.
[29] B. Lakzaei, M. H. Chehreghani, and A. Bagheri, “A Decision-Based Heterogenous Graph Attention Network for Multi-Class Fake News Detection,” arXiv, Jan. 2025.
[30] S. Ni, J. Li, and H.-Y. Kao, “MVAN: Multi-view attention networks for fake news detection on social media,” IEEE Access, vol. 9, pp. 106907–106917, 2021, doi: 10.1109/ACCESS.2021.3100245.
[31] Saif Wali Ali Alsudani and Adel Ghazikhani, “Enhancing Intrusion Detection with LSTM Recurrent Neural Network Optimized by Emperor Penguin Algorithm”, WJCMS, vol. 2, no. 3, pp. 69–80, Sep. 2023, doi: 10.31185/wjcms.166.
[32] S. W. A. Alsudani and G. K. Saud, “Recurrent neural network optimized by grasshopper for accurate audio data-based diagnosis of Parkinson’s disease,” WJPS, vol. 4, no. 2, pp. 56–75, Jun. 2025, doi: 10.31185/wjps.766.
[33] P. N. Ahmad, J. Guo, N. M. AboElenein, et al., “Hierarchical graph-based integration network for propaganda detection in textual news articles on social media,” Scientific Reports, vol. 15, Art. no. 1827, 2025, doi: 10.1038/s41598-024-74126-9.
[34] J. Cao, S. Zhuo, J. Su, and G. Chen, “A fake news detection model based on capsule networks and collaborative attention,” Applied Sciences, vol. 15, no. 22, p. 12190, 2025, doi: 10.3390/app152212190.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Karrar Kanaan
This work is licensed under a Creative Commons Attribution 4.0 International License.
