2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 18 , Issue 2 , PP: 205-219, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Vanitha Siddheswaran 1 * , Prabahari Raju 2
Doi: https://doi.org/10.54216/JISIoT.180215
Internet and social media have become significant platforms for sharing real-time information, with rumors significantly affecting billions of people's perceptions. Considerably, Rumor recognition is the most challenging task on social media platforms. Numerous Deep Learning (DL) models have been developed to extract linguistic characteristics from short-text tweets for rumor prediction. However, these models struggles to capture the intricate spatiotemporal relationships presenting tweet interactions. To address this issues, Bidirectional Encoder Representation from Transformers with Attention based Balanced Spatial-Temporal Graph Convolutional Networks (BERT-ABSTGCN) was used. This model incorporates Spatial-Temporal Attention Mechanism (STAM) and a Spatial-Temporal Convolution Module (STCM) to effectively model the spatiotemporal dependencies within in tweet interactions to enhance rumor detection. However, it constitutes to high degradation problem due to convergence issues. A popular solution to these problems is Residual Learning (RL), which introduces identity mappings to speed up training and enhance gradient propagation. However, traditional RL can only be used for layer-wise task refining, which severely restricts its capacity to grasp more generalized dependencies. However, conventional RL is restricted to layer-wise refinement within a single task limiting its ability to capture broader dependencies. To address this, the proposed work is included with a Cross-Residual Learning (CRL) in BERT-ABSTGCN named BERT with Attention-based Balanced Spatial-Temporal Residual Graph Convolutional Networks (BERT-ABSTRGCN) for efficient rumor detection and stance classification. CRL of BERT-ABSTRGCN enable intuitive learning across multiple tasks like rumor detection and stance classification using cross-connections. CRL establishes direct connections between shallow and deep feature representations, mitigating the vanishing gradient issue. The fitted residual mappings in the CRL will facilitate the BERT- BERT-ABSTRGCN with the provided information by using the short cut connections and lowers the probability of model degradation. BERT-ABSTRGCN effectively identifies rumor with different stances about specific social media posts, thereby preventing the spread of rumors. Experimental evaluations show that BERT-ABSTRGCN achieves 95.62% accuracy on the PHEME dataset and 90.15% on Mendeley’s COVID-19 rumor dataset, significantly surpassing traditional models.
Rumor recognition , Graph Convolutional Networks , Attention Mechanism , Cross Residual Learning , Stance Classifcation
[1] Z. H. Ali, H. A. Ali, and M. M. Badawy, "Internet of Things (IoT): definitions, challenges and recent research directions," Int. J. Comput. Appl., vol. 128, no. 1, pp. 37-47, 2015.
[2] L. Atzori, A. Iera, G. Morabito, and M. Nitti, "The social internet of things (SIoT)–when social networks meet the internet of things: Concept, architecture and network characterization," Comput. Netw, vol. 56, no. 16, pp. 3594-3608, 2012.
[3] M. S. Roopa, S. Pattar, R. Buyya, K. R. Venugopal, S. S. Iyengar, and L. M. Patnaik, "Social Internet of Things (SIoT): Foundations, thrust areas, systematic review and future directions," Comput. Commun, vol. 139, pp. 32-57, 2019.
[4] Dang, M. Smit, A. Moh'd, R. Minghim, and E. Milios, "Toward understanding how users respond to rumours in social media," in Proc. IEEE/ACM Int. Conf. Adv. Soc. Netw. Anal. Mining (ASONAM), 2016, pp. 777-784.
[5] P. Zheng, Z. Huang, Y. Dou, and Y. Yan, "Rumor detection on social media through mining the social circles with high homogeneity," Inf. Sci., vol. 642, p. 119083, 2023.
[6] N. Alturayeif, H. Luqman, and M. Ahmed, "A systematic review of machine learning techniques for stance detection and its applications," Neural Comput. Appl., vol. 35, no. 7, pp. 5113-5144, 2023.
[7] AlDayel and W. Magdy, "Stance detection on social media: State of the art and trends," Inf. Process. Manag, vol. 58, no. 4, p. 102597, 2021.
[8] H. F. Alsaif and H. D. Aldossari, "Review of stance detection for rumor verification in social media," Eng. Appl. Artif. Intell., vol. 119, p. 105801, 2023.
[9] Z. Mohammadhosseini and A. Jalaly Bidgoly, "Efficient Stance Ordering to Improve Rumor Veracity Detection," J. AI Data Min., vol. 11, no. 1, pp. 69-76, 2023.
[10] B. Pattanaik, S. Mandal, and R. M. Tripathy, "A survey on rumor detection and prevention in social media using deep learning," Knowl. Inf. Syst., pp. 1-42, 2023.
[11] Kumar, M. P. S. Bhatia, and S. R. Sangwan, "Rumour detection using deep learning and filter-wrapper feature selection in benchmark twitter dataset," Multimedia Tools Appl., vol. 81, no. 24, pp. 34615-34632, 2022.
[12] Z. Luo, Q. Li, and J. Zheng, "Deep feature fusion for rumor detection on twitter," IEEE Access, vol. 9, pp. 126065-126074, 2021.
[13] Z. Zojaji and B. Tork Ladani, "Adaptive cost-sensitive stance classification model for rumor detection in social networks," Soc. Netw. Anal. Min., vol. 12, no. 1, p. 134, 2022.
[14] S. Roy, M. Bhanu, S. Dandapat, and J. Chandra, "Towards an orthogonality constraint-based feature partitioning approach to classify veracity and identify stance overlapping of rumors on twitter," Expert Syst. Appl., vol. 208, p. 118175, 2022.
[15] W. Cui and M. Shang, "KAGN: knowledge-powered attention and graph convolutional networks for social media rumor detection," J. Big Data, vol. 10, no. 1, p. 45, 2023.
[16] Z. Chen, L. Wang, X. Zhu, and S. Dietze, "TSNN: A Topic and Structure Aware Neural Network for Rumor Detection," Neurocomputing, vol. 531, pp. 114-124, 2020.
[17] N. Bai, F. Meng, X. Rui, and Z. Wang, "A multi-task attention tree neural net for stance classification and rumor veracity detection," Appl. Intell., vol. 53, no. 9, pp. 10715-10725, 2023.
[18] N. Alturayeif, H. Luqman, and M. Ahmed, "Enhancing stance detection through sequential weighted multi-task learning," Soc. Netw. Anal. Min., vol. 14, no. 1, p. 7, 2023.
[19] W. Feng, Y. Li, B. Li, Z. Jia, and Z. Chu, "BiMGCL: rumor detection via bi-directional multi-level graph contrastive learning," PeerJ Comput. Sci., p. e1659, 2023.
[20] Y. Zhu, G. Wang, S. Li, and X. Huang, "A Novel Rumor Detection Method Based on Non-Consecutive Semantic Features and Comment Stance," IEEE Access, vol. 11, pp. 1-9, 2023.
[21] H. Li, W. Yang, H. Wang, and W. Wang, "FSRD: few-shot fuzzy rumor detection system with stance-enhanced prompt learning," Soft Comput., pp. 1-15, 2024.
[22] N. Luo, D. Xie, Y. Mo, F. Li, C. Teng, and D. Ji, "Joint rumor and stance identification based on semantic and structural information in social networks," Appl. Intell., vol. 54, no. 1, pp. 264-282, 2024.
[23] G. Ma, C. Hu, L. Ge, and H. Zhang, "DSMM: A dual stance-aware multi-task model for rumour veracity on social networks," Inf. Process. Manag, vol. 61, no. 1, p. 103528, 2024.
[24] N. Michelle, "PHEME dataset for rumour detection," Kaggle, 2021. [Online]. Available: https://www.kaggle.com/datasets/nicolemichelle/pheme-dataset-for-rumour-detection
[25] B. Janssens, L. Schetgen, M. Bogaert, M. Meire, and D. Van den Poel, "COVID-19 rumor detection," Mendeley Data, V1, 2022. [Online]. Available: https://data.mendeley.com/datasets/xcz8vb448y/1
