Abstract
Misinformation proliferates on social media platforms owing to both static and dynamic user populations, where the set of active users and their interactions evolve over time. The development, amalgamation, or disintegration of communities throughout an information cascade complicates the longitudinal tracking of these communities. Numerous contemporary methodologies either neglect temporal factors or employ static clustering techniques, which do not accommodate dynamic coordination. We propose TIDE-MARK, a methodology designed to identify communities inside fake news cascades that exhibit consistency in both structure and temporal dynamics. The methodology encompasses node embeddings via temporal graph neural networks, prototype-driven clustering, Markov modeling of community transitions, and reinforcement-based refinement. The unified design facilitates consistent and comprehensible community trajectories. Three empirical datasets pertaining to political, entertainment, and health-related fake news are utilized to evaluate TIDE-MARK. The databases include PolitiFact, GossipCop, and ReCOVery. Our model surpasses robust baselines regarding structural (modularity, conductance) and temporal (adjusted Rand index) measures, supported by consistent effect sizes. Structural research indicates that real news spreads through more scattered and less organized communities, while false news propagates through more stable and well interconnected communities. Our objective is to assess the viability of interventions by simulating a structure-aware approach that targets important users in nascent communities. The substantial reduction in cascade modularity and spread demonstrated in the results demonstrates the potential viability of content-neutral mitigation techniques. TIDE-MARK offers a structure-aware framework for real-time fake news monitoring, emphasizing network-based strategy signals over textual analysis. It establishes a foundation for innovative methods of dynamic community monitoring inside complex social systems and features an interpretable architecture that enables ethical application.
Similar content being viewed by others
Data availability
The datasets used and/or analysed during the current study available from the corresponding author on reasonable request.
Code availability
A minimal reproducible version of the code used in this study is provided as Supplementary Material. This implementation is intended to support methodological transparency and conceptual reproducibility of the proposed framework.
References
Vosoughi, S., Roy, D. & Aral, S. The spread of true and false news online. Science 359, 1146–1151 (2018).
Ferrara, E., Cresci, S. & Luceri, L. Misinformation, manipulation, and abuse on social media in the era of covid-19. J. Comput. Soc. Sci. 3, 271–277 (2020).
Rossetti, G. & Cazabet, R. Community discovery in dynamic networks: a survey. ACM Comput. Surv. (CSUR) 51, 1–37 (2018).
Holme, P. & Saramäki, J. Temporal networks. Phys. Rep. 519, 97–125 (2012).
Papanastasiou, Y. Fake news propagation and detection: a sequential model. Manage. Sci. 66, 1826–1846 (2020).
Shao, C. et al. The spread of low-credibility content by social bots. Nat. Commun. 9, 4787 (2018).
Cinelli, M. et al. The covid-19 social media infodemic. Sci. Rep. 10, 16598 (2020).
Ferrara, E., Chang, H., Chen, E., Muric, G. & Patel, J. Characterizing social media manipulation in the 2020 us presidential election. First Monday (2020).
Shao, C. et al. Anatomy of an online misinformation network. PLoS ONE 13, e0196087 (2018).
Juul, J. L. & Ugander, J. Comparing information diffusion mechanisms by matching on cascade size. Proc. Natl. Acad. Sci. 118, e2100786118 (2021).
Pick, R. K., Kozhukhov, V., Vilenchik, D. & Tsur, O. Stem: unsupervised structural embedding for stance detection. In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36 11174–11182 (2022).
Barel, G., Tsur, O. & Vilenchik, D. Acquired TASTE: multimodal stance detection with textual and structural embeddings. In Proceedings of the 31st International Conference on Computational Linguistics 6492–6504 (Association for Computational Linguistics, 2025).
Shu, K., Mahudeswaran, D., Wang, S., Lee, D. & Liu, H. Fakenewsnet: a data repository with news content, social context, and spatiotemporal information for studying fake news on social media. Big Data 8, 171–188 (2020).
Zhou, X., Mulay, A., Ferrara, E. & Zafarani, R. Recovery: a multimodal repository for covid-19 news credibility research. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management 3205–3212 (2020).
Blondel, V. D., Guillaume, J.-L., Lambiotte, R. & Lefebvre, E. Fast unfolding of communities in large networks. J. Stat. Mech: Theory Exp. 2008, P10008 (2008).
Rosvall, M. & Bergstrom, C. T. Maps of random walks on complex networks reveal community structure. Proc. Natl. Acad. Sci. 105, 1118–1123 (2008).
Cazabet, R. & Rossetti, G. Challenges in community discovery on temporal networks. In Temporal Network Theory 185–202 (Springer, 2023).
Yuan, L. et al. Temporal community detection and analysis with network embeddings. Mathematics 13, 698 (2025).
Rabiner, L. & Juang, B. An introduction to hidden markov models. IEEE ASSP Mag. 3, 4–16 (1986).
Mucha, P. J., Richardson, T., Macon, K., Porter, M. A. & Onnela, J.-P. Community structure in time-dependent, multiscale, and multiplex networks. Science 328, 876–878 (2010).
Pareja, A. et al. Evolvegcn: Evolving graph convolutional networks for dynamic graphs. In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34 5363–5370 (2020).
Rossi, E. et al. Temporal graph networks for deep learning on dynamic graphs. arXiv preprint arXiv:2006.10637 (2020).
Gupta, S. & Kundu, S. Communities in streaming graphs: small space data structure, benchmark data generation, and linear algorithm. ACM Trans. Knowl. Discov. Data 19, 1–24 (2025).
Newman, M. E. Modularity and community structure in networks. Proc. Natl. Acad. Sci. 103, 8577–8582 (2006).
Shi, J. & Malik, J. Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22, 888–905 (2000).
Cazabet, R., Rossetti, G. & Amblard, F. Dynamic community detection. In Encyclopedia of Social Network Analysis and Mining 669–678 (Springer, 2018).
Chi, Y., Song, X., Zhou, D., Hino, K. & Tseng, B. L. Evolutionary spectral clustering by incorporating temporal smoothness. In Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 153–162 (2007).
Sankar, A., Wu, Y., Gou, L., Zhang, W. & Yang, H. Dysat: deep neural representation learning on dynamic graphs via self-attention networks. In Proceedings of the 13th ACM International Conference on Web Search and Data Mining (WSDM) 519–527 (2020).
Xu, D., Ruan, C., Körpeoglu, E., Kumar, S. & Achan, K. Inductive representation learning on temporal graphs. In Proceedings of the 8th International Conference on Learning Representations (ICLR 2020) (2020).
Zuo, Y. et al. Embedding temporal network via neighborhood formation. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2857–2866 (2018).
Liu, H., Ling, Z. & Qu, D. Lstm-based hazard source detection and risk assessment model for the shandong yellow river basin. In Proceedings of the Fifth International Conference on Computer Vision and Pattern Analysis (ICCPA), vol. 13733 137330P (SPIE, 2025). https://doi.org/10.1117/12.3076328.
Yang, Y. et al. Link-based attributed graph clustering via approximate generative bayesian learning. IEEE Trans. Systems Man Cybern. Syst. (2025).
Yang, Y. et al. Fmvpci: a multiview fusion neural network for identifying protein complex via fuzzy clustering. IEEE Trans. Systems Man Cybern. Syst. (2025).
Ma, J., Gao, W. & Wong, K.-F. Detect rumors on twitter by promoting information campaigns with generative adversarial learning. In The World Wide Web Conference 3049–3055 (2019).
Wu, L., Morstatter, F., Carley, K. M. & Liu, H. Misinformation in social media: definition, manipulation, and detection. ACM SIGKDD Explor. Newsl. 21, 80–90 (2019).
Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. Bert: pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, volume 1 (long and short papers) 4171–4186 (2019).
Cho, K. et al. Learning phrase representations using RNN encoder–decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) 1724–1734 (Association for Computational Linguistics, 2014). https://doi.org/10.3115/v1/D14-1179.
Traag, V. A., Waltman, L. & Van Eck, N. J. From louvain to leiden: guaranteeing well-connected communities. Sci. Rep. 9, 1–12 (2019).
Norris, J. R. Markov Chains (Cambridge University Press, 1998).
Efron, B. & Tibshirani, R. J. An Introduction to the Bootstrap (Chapman and Hall/CRC, 1994).
Xie, J., Chen, M. & Szymanski, B. K. Labelrankt: incremental community detection in dynamic networks via label propagation. In Proceedings of the Workshop on Dynamic Networks Management and Mining 25–32 (2013).
Kitsak, M. et al. Identification of influential spreaders in complex networks. Nat. Phys. 6, 888–893 (2010).
Pastor-Satorras, R., Castellano, C., Van Mieghem, P. & Vespignani, A. Epidemic processes in complex networks. Rev. Mod. Phys. 87, 925–979 (2015).
Davison, A. C. & Hinkley, D. V. Bootstrap Methods and Their Application (Cambridge University Press, 1997).
Mazza, M., Cola, G. & Tesconi, M. Modularity-based approach for tracking communities in dynamic social networks. Knowl.-Based Syst. 281, 111067 (2023).
Funding
There is no funding for this research.
Author information
Authors and Affiliations
Contributions
Y.M. and D.Q. contributed equally to this work. Y.M. and D.Q conceived the experiment(s), Y.M. and D.Q. conducted the experiment(s), Y.W. and D.Q. analysed the results. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Ma, Y., Qu, D. & Wang, Y. Tracking evolving communities in fake news cascades using temporal graphs. Sci Rep (2026). https://doi.org/10.1038/s41598-026-35175-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-35175-4
