FNDMFF: Enhancing Fake News Detection via Multi-Source Feature Fusion Framework
DOI:
https://doi.org/10.70715/jitcai.2026.v3.i2.055Keywords:
Fake news detection, Hypergraph neural network, Multi-source feature fusion, Propagation graph, Attention mechanismAbstract
Current approaches to identifying fake news frequently overlook the comprehensive utilization of layered characteristics or fail to capture advanced relational patterns during information dissemination. In response, we introduce FNDMFF, a framework designed to improve fake news identification by integrating structural, temporal, and textual features through a specialized gating mechanism for multi-source integration. The process begins by extracting dissemination structures via an improved hypergraph neural network, followed by analyzing temporal patterns with a variable-scale timing component, and concludes by extracting textual details using a multi-head attention approach. In particular, FNDMFF includes a gating unit for feature fusion that adaptively modifies the importance of various feature aspects, allowing for the seamless integration of diverse data types. Tests on the Politifact and Twitter16 datasets reveal that FNDMFF surpasses established models such as UPFD, HGNN, and the state-of-the-art RTRUST method. Our system delivers a 3.63% boost in precision and a 3.40% gain in F1-score for Politifact, alongside 0.54% and 0.55% enhancements for Twitter16. This highlights the value of fusing multiple data sources for detecting misinformation.
Downloads
References
[1] F. Olan, U. Jayawickrama, and E. O. Arakpogun, "Fake news on social media: The impact on society," Information Systems Frontiers, vol. 26, no. 2, pp. 443-458, 2024, doi: 10.1007/s10796-022-10242-z. DOI: https://doi.org/10.1007/s10796-022-10242-z
[2] H. Sun, J. Tang, and S. Dang, "Privacy and distribution preserving generative adversarial networks with sample balancing," Expert Systems with Applications, vol. 258, p. 125181, 2024, doi: 10.1016/j.eswa.2024.125181. DOI: https://doi.org/10.1016/j.eswa.2024.125181
[3] E. Broda and J. Strömbäck, "Misinformation, disinformation, and fake news: lessons from an interdisciplinary, systematic literature review," Annals of the International Communication Association, vol. 48, 03/06 2024, doi: 10.1080/23808985.2024.2323736. DOI: https://doi.org/10.1080/23808985.2024.2323736
[4] J. Alghamdi, Y. Lin, and S. Luo, "Towards COVID-19 fake news detection using transformer-based models," Knowledge-Based Systems, vol. 274, p. 110642, 2023, doi: 10.1016/j.knosys.2023.110642. DOI: https://doi.org/10.1016/j.knosys.2023.110642
[5] S. Raza and C. Ding, "Fake news detection based on news content and social contexts: A transformer-based approach," International Journal of Data Science and Analytics, vol. 13, no. 4, pp. 335-362, 2022, doi: 10.1007/s41060-021-00302-z. DOI: https://doi.org/10.1007/s41060-021-00302-z
[6] N. Ruchansky, S. Seo, and Y. Liu, "CSI: A hybrid deep model for fake news detection," in 2017 ACM on Conference on Information and Knowledge Management, 2017, pp. 797-806, doi: 10.1145/3132847.3132877. DOI: https://doi.org/10.1145/3132847.3132877
[7] K. Shu, L. Cui, and S. Wang, "dEFEND: Explainable fake news detection," in The 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 395-405, doi: 10.1145/3292500.3330935. DOI: https://doi.org/10.1145/3292500.3330935
[8] G. Hu, G. Lu, and Y. Zhao, "Bidirectional hierarchical attention networks based on document-level context for emotion cause extraction," in Findings of the Association for Computational Linguistics: EMNLP 2021, 2021, pp. 558-568, doi: 10.18653/v1/2021.findings-emnlp.51. DOI: https://doi.org/10.18653/v1/2021.findings-emnlp.51
[9] J. Vatter, R. Mayer, and H. A. Jacobsen, "The evolution of distributed systems for graph neural networks and their origin in graph processing and deep learning: A survey," ACM Computing Surveys, vol. 56, no. 1, p. 6, 2023, doi: 10.1145/3597428. DOI: https://doi.org/10.1145/3597428
[10] Z. Wu, S. Pan, and F. Chen, "A comprehensive survey on graph neural networks," IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 1, pp. 4-24, 2021, doi: 10.1109/TNNLS.2020.2978386. DOI: https://doi.org/10.1109/TNNLS.2020.2978386
[11] U. A. Bhatti, H. Tang, and G. Wu, "Deep learning with graph convolutional networks: An overview and latest applications in computational intelligence," International Journal of Intelligent Systems, vol. 2023, no. 1, p. 8342104, 2023, doi: 10.1155/2023/8342104. DOI: https://doi.org/10.1155/2023/8342104
[12] Z. Li, Y. Zhao, and Y. Zhang, "Multi-relational graph attention networks for knowledge graph completion," Knowledge-Based Systems, vol. 251, p. 109262, 2022, doi: 10.1016/j.knosys.2022.109262. DOI: https://doi.org/10.1016/j.knosys.2022.109262
[13] H. Wu, Z. Zhang, and S. Shi, "Phrase dependency relational graph attention network for aspect-based sentiment analysis," Knowledge-Based Systems, vol. 236, p. 107736, 2022, doi: 10.1016/j.knosys.2021.107736. DOI: https://doi.org/10.1016/j.knosys.2021.107736
[14] Y. Han, S. Karunasekera, and C. Leckie, "Graph neural networks with continual learning for fake news detection from social media," arXiv preprint arXiv:2007.03316, 2020. DOI: https://doi.org/10.1007/978-3-030-86340-1_30
[15] T. Bian, X. Xiao, and T. Xu, "Rumor detection on social media with bi-directional graph convolutional networks," in The 34th AAAI Conference on Artificial Intelligence, 2020, pp. 549-556, doi: 10.1609/aaai.v34i01.5393. DOI: https://doi.org/10.1609/aaai.v34i01.5393
[16] F. Monti, F. Frasca, and D. Eynard, "Fake news detection on social media using geometric deep learning," arXiv preprint arXiv:1902.06673, 2019.
[17] Y. Dou, K. Shu, and C. Xia, "User preference-aware fake news detection," in The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021, pp. 2051-2055, doi: 10.1145/3404835.3462990. DOI: https://doi.org/10.1145/3404835.3462990
[18] Y. Ren and J. Zhang, "Fake news detection on news-oriented heterogeneous information networks through hierarchical graph attention," in 2021 International Joint Conference on Neural Networks (IJCNN), 2021, pp. 1-8, doi: 10.1109/IJCNN52387.2021.9534362. DOI: https://doi.org/10.1109/IJCNN52387.2021.9534362
[19] S. Bai, F. Zhang, and P. H. S. Torr, "Hypergraph convolution and hypergraph attention," Pattern Recognition, vol. 110, p. 107637, 2021, doi: 10.1016/j.patcog.2020.107637. DOI: https://doi.org/10.1016/j.patcog.2020.107637
[20] G. Lee, F. Bu, T. Eliassi-Rad, and K. Shin, "A Survey on Hypergraph Mining: Patterns, Tools, and Generators," ACM Comput. Surv., vol. 57, no. 8, mar, articleno = 203 , numpages = 36 2025, doi: 10.1145/3719002. DOI: https://doi.org/10.1145/3719002
[21] D. Sakong, V. H. Vu, and T. T. Huynh, "Higher-order knowledge-enhanced recommendation with heterogeneous hypergraph multi-attention," Information Sciences, vol. 680, p. 121165, 2024, doi: 10.1016/j.ins.2024.121165. DOI: https://doi.org/10.1016/j.ins.2024.121165
[22] M. Wang, W. Liu, and X. Yuan, "Parallel hypergraph convolutional neural networks for image annotation," in 2022 41st Chinese Control Conference (CCC), 2022, pp. 6582-6587, doi: 10.23919/CCC55666.2022.9901938. DOI: https://doi.org/10.23919/CCC55666.2022.9901938
[23] Y. Jin, W. Yin, and H. Wang, "Capturing word positions does help: A multi-element hypergraph gated attention network for document classification," Expert Systems with Applications, vol. 251, p. 124002, 2024, doi: 10.1016/j.eswa.2024.124002. DOI: https://doi.org/10.1016/j.eswa.2024.124002
[24] J. Ma, W. Gao, and K.-F. Wong, "Rumor Detection on Twitter with Tree-structured Recursive Neural Networks," Melbourne, Australia, July 2018: Association for Computational Linguistics, in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1980-1989, doi: 10.18653/v1/P18-1184. [Online]. Available: https://aclanthology.org/P18-1184/
https://doi.org/10.18653/v1/P18-1184 DOI: https://doi.org/10.18653/v1/P18-1184
[25] N. Jiang, Z. Tu, and K. Pei, "RTrust: Toward robust trust evaluation framework for fake news detection in online social networks," World Wide Web, vol. 27, no. 6, p. 76, 2024, doi: 10.1007/s11280-024-01317-9. DOI: https://doi.org/10.1007/s11280-024-01317-9
[26] S. Yun, M. Jeong, R. Kim, J. Kang, and H. Kim, Graph Transformer Networks. 2019.
[27] J. Hu, J. Zhang, and Z. Li, "Tracing truth: dynamic temporal networks for multi-modal fake news detection," (in eng), PeerJ Comput Sci, vol. 11, p. e2998, 2025, doi: 10.7717/peerj-cs.2998. DOI: https://doi.org/10.7717/peerj-cs.2998
[28] U. Jeong, K. Ding, and L. Cheng, "Nothing stands alone: Relational fake news detection with hypergraph neural networks," in 2022 IEEE International Conference on Big Data (Big Data), 2022, pp. 596-605, doi: 10.1109/BigData55660.2022.10020234. DOI: https://doi.org/10.1109/BigData55660.2022.10020234
[29] C. Zhang, A. Gupta, and X. Qin, "A computational approach for real-time detection of fake news," Expert Systems with Applications, vol. 221, p. 119656, 2023, doi: 10.1016/j.eswa.2023.119656. DOI: https://doi.org/10.1016/j.eswa.2023.119656
[30] M. R. Kondamudi, S. R. Sahoo, and L. Chouhan, "A comprehensive survey of fake news in social networks: Attributes, features, and detection approaches," Journal of King Saud University-Computer and Information Sciences, vol. 35, no. 6, p. 101571, 2023, doi: 10.1016/j.jksuci.2023.101571. DOI: https://doi.org/10.1016/j.jksuci.2023.101571
[31] Y. Zhang, L. Ma, and S. Pal, "Multi-resolution time-series transformer for long-term forecasting," in The 27th International Conference on Artificial Intelligence and Statistics, 2024, pp. 4222-4230.
[32] M. Hassanin, S. Anwar, and I. Radwan, "Visual attention methods in deep learning: An in-depth survey," Information Fusion, vol. 108, p. 102417, 2024, doi: 10.1016/j.inffus.2024.102417. DOI: https://doi.org/10.1016/j.inffus.2024.102417
[33] K. T. Chitty-Venkata, S. Mittal, and M. Emani, "A survey of techniques for optimizing transformer inference," Journal of Systems Architecture, vol. 144, p. 102990, 2023, doi: 10.1016/j.sysarc.2023.102990. DOI: https://doi.org/10.1016/j.sysarc.2023.102990
[34] H. Yang, J. Zhang, and L. Zhang, "MRAN: Multimodal relationship-aware attention network for fake news detection," Computer Standards & Interfaces, vol. 89, p. 103822, 2024, doi: 10.1016/j.csi.2023.103822. DOI: https://doi.org/10.1016/j.csi.2023.103822
[35] C. Song, K. Shu, and B. Wu, "Temporally evolving graph neural network for fake news detection," Information Processing & Management, vol. 58, no. 6, p. 102712, 2021, doi: 10.1016/j.ipm.2021.102712. DOI: https://doi.org/10.1016/j.ipm.2021.102712
[36] H. Matsumoto, S. Yoshida, and M. Muneyasu, "Propagation-based fake news detection using graph neural networks with transformer," in 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE), 2021, pp. 19-20, doi: 10.1109/GCCE53005.2021.9621803. DOI: https://doi.org/10.1109/GCCE53005.2021.9621803
[37] Y. Feng, H. You, Z. Zhang, R. Ji, and Y. Gao, "Hypergraph neural networks," presented at the Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence , articleno = 437 , numpages = 8, 2019. [Online]. Available: https://doi.org/10.1609/aaai.v33i01.33013558. DOI: https://doi.org/10.1609/aaai.v33i01.33013558
[38] W. L. Hamilton, R. Ying, and J. Leskovec, "Inductive representation learning on large graphs," in The 31st International Conference on Neural Information Processing Systems, 2017, pp. 1025-1035.
Downloads
Published
Data Availability Statement
The datasets employed in this study are publicly accessible through online repositories.
Issue
Section
Categories
License
Copyright (c) 2026 Dr. Hani Iwidat (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
