Multi-Task Rumor Detection Method Based on Time-Step Dynamic Interaction

doi:10.3778/j.issn.1002-8331.2310-0333

Abstract

Abstract: Rumour detection aims to identify information on social media that has not been officially verified or artificially created. Today’s social networks contain a pattern of dynamic relationships that are difficult to find, changing over time and dynamic interactions between different posts. This paper proposes a multi-task rumour detection method based on time step local dynamic interaction, which can capture the hidden dynamic correlation information in rumour spreading events. An efficient multi-task interaction method is designed, in which time step is used as the basic sharing unit, the local features learned are shared, and the sharing efficiency is greatly improved, so that the detection framework of local dynamic interaction and whole multi-task sharing is formed. Finally, the attention mechanism is used to filter the information that is more favorable for rumour detection in different tasks and different structural characteristics to improve the detection effect. Experiments on PHEME and WEIBO datasets show that this method has advanced performance.

Key words: rumor detection, time-step local dynamic interactions, propagation structure characterization, multitask sharing

摘要： 谣言检测旨鉴别社交媒体中未经官方证实或人为捏造的信息，而当今社交网络中隐含着一种难以发掘的动态关系模式，它随时间推移和不同帖子间的动态交互而变化。针对现有方法对谣言传播事件中隐含的动态特征和关联信息考虑不充分的问题，提出一种基于时间步局部动态交互的多任务谣言检测方法，能捕获谣言传播事件中隐含的动态关联信息；并设计了一种高效的多任务交互方式，以时间步为基本共享单元，将学习到的局部特征进行共享，极大提升了共享效率，从而形成局部动态交互，整体多任务共享的检测框架。最后利用注意力机制筛选不同任务、不同结构特征中对谣言检测更有利的信息，以提升检测效果。在PHEME和WEIBO数据集上进行了实验，结果表明该方法具有较先进的性能。

关键词: 谣言检测, 时间步局部动态交互, 传播结构特征, 多任务共享

YANG Guanghao, WAN Shuzhen, DONG Fangmin, WANG Mengyuan. Multi-Task Rumor Detection Method Based on Time-Step Dynamic Interaction[J]. Computer Engineering and Applications, 2025, 61(6): 183-191.

杨广浩, 万书振, 董方敏, 王梦园. 基于时间步局部动态交互的多任务谣言检测方法[J]. 计算机工程与应用, 2025, 61(6): 183-191.

References

[1] DIFONZO N, BORDIA P. Rumor psychology: social and organizational approaches[EB/OL].(2007). American Psychological Association. https://doi.org/10.1037/11503-000.
[2] COHEN J, NORMILE D. New SARS-like virus in China triggers alarm[J]. Science, 2020, 367(6475): 234-235.
[3] MA J, GAO W, MITRA P, et al. Detecting rumors from microblogs with recurrent neural networks[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI 2016), 2016: 3818-3824.
[4] AHMAD T, FAISAL M S, RIZWAN A, et al. Efficient fake news detection mechanism using enhanced deep learning model[J]. Applied Sciences, 2022, 12(3): 1743.
[5] BIAN T, XIAO X, XU T Y, et al. Rumor detection on social media with bi-directional graph convolutional networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 549-556.
[6] BAI N, MENG F R, RUI X B, et al. Rumor detection based on a source-replies conversation tree convolutional neural net[J]. Computing, 2022, 104: 1155-1171.
[7] MA J, GAO W, WONG K F. Rumor detection on twitter with tree-structured recursive neural networks[C]//Proceedings of the Association for Computational Linguistics, 2018.
[8] VAIBHAV V, ANNASAMY R M, HOVY E. Do sentence interactions matter? leveraging sentence level representations for fake news classification[J]. arXiv:1910.12203, 2019.
[9] ZHOU X, ZAFARANI R. A survey of fake news: fundamental theories, detection methods, and opportunities[J]. ACM Computing Surveys (CSUR), 2020, 53(5): 1-40.
[10] MA J, GAO W, WONG K F. Detect rumor and stance jointly by neural multi-task learning[C]//Proceedings of the Web Conference, 2018: 585-593.
[11] WAN S Z, TANG B, DONG F M, et al. A writing style-based multi-task model with the hierarchical attention for rumor detection[J]. International Journal of Machine Learning and Cybernetics, 2023, 14: 3993-4008.
[12] KOCHKINA E, LIAKATA M, ZUBIAGA A. All-in-one: multi-task learning for rumour verification[J]. arXiv:1806. 03713, 2018.
[13] SINGH J P, KUMAR A, RANA N P, et al. Attention-based LSTM network for rumor veracity estimation of tweets[J]. Information Systems Frontiers, 2020, 24: 459-474.
[14] 郭铃霓, 黄舰, 吴兴财, 等. 基于双分支网络联合训练的虚假新闻检测[J]. 计算机工程与应用，2022, 58(15): 153-161.
GUO L N, HUANG J, WU X C, et al. Fake news detection based on joint training two-branch network[J]. Computer Engineering and Applications, 2022, 58(15): 153-161.
[15] 戚力鑫, 万书振, 唐斌, 等. 基于注意力机制的多模态融合谣言检测方法[J]计算机工程与应用, 2022, 58(19): 209-217.
QI L X, WAN S Z, TANG B, et al. Multimodal fusion rumor detection method based on attention mechanism[J]. Computer Engineering and Applications, 2022, 58(19): 209-217.
[16] 邱宁佳, 杨长庚, 王鹏, 等. 改进卷积神经网络的文本主题识别算法研究[J]. 计算机工程与应用, 2022, 58(2): 161-168.
QIU N J, YANG C G, WANG P, et al. Research on text topic recognition algorithm based on improved convolutional neural network[J]. Computer Engineering and Applications, 2022, 58(2): 161-168.
[17] LIAO H, PENG J H, HUANG Z Y, et al. MUSER: a multi-step evidence retrieval enhancement framework for fake news detection[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023: 4461-4472.
[18] CHEN Z W, HU L M, LI W X, et al. Causal intervention and counterfactual reasoning for multi-modal fake news detection[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023: 627-638.
[19] ZHANG P F, RAN H Y, JIA C Y, et al. A lightweight propagation path aggregating network with neural topic model for rumor detection[J]. Neurocomputing, 2021, 458: 468-477.
[20] WU Z Y, PI D C, CHEN J F, et al. Rumor detection based on propagation graph neural network with attention mechanism[J]. Expert Systems with Applications, 2020, 158: 113595.
[21] RAN H Y, JIA C Y, ZHANG P F, et al. MGAT-ESM: multi-channel graph attention neural network with event-sharing module for rumor detection[J]. Information Sciences, 2022, 592: 402-416.
[22] WU J Y, HOOI B. DECOR: degree-corrected social graph refinement for fake news detection[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023: 2582-2593.
[23] ZHANG Y, YANG Q. A survey on multi-task learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 34(12): 5586-5609.
[24] 沈瑞琳, 潘伟民, 彭成. 基于多任务学习的微博谣言检测方法[J]. 计算机工程与应用, 2021, 57(24): 192-197.
SHEN R L, PAN W M, PENG C. Microblog rumor detection method based on multi-task learning[J]. Computer Engineering and Applications, 2021, 57(24): 192-197.
[25] COLLOBERT R, WESTON J. A unified architecture for natural language processing: deep neural networks with multitask learning[C]//Proceedings of the 25th International Conference on Machine Learning, 2008: 160-167.
[26] SUN L, RAO Y, LAN Y Q, et al. HG-SL: jointly learning of global and local user spreading behavior for fake news early detection[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2023: 5248-5256.
[27] CASTILLO C, MENDOZA M, POBLETE B. Information credibility on twitter[C]//Proceedings of the 20th International Conference on World Wide Web, 2011: 675-684.
[28] YANG F, LIU Y, YU X H, et al. Automatic detection of rumor on sina weibo[C]//Proceedings of the ACM SIGKDD Workshop on Mining Data Semantics, 2012: 1-7.
[29] MA J, GAO W, WEI Z Y, et al. Detect rumors using time series of social context information on microblogging websites[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, 2015: 1751-1754.
[30] HUANG Q, ZHOU C, WU J, et al. Deep spatial-temporal structure learning for rumor detection on Twitter[J]. Neural Computing and Applications, 2020, 35(3): 05236.
[31] SUN M Z, ZHANG X, ZHENG J Q, et al. DDGCN: dual dynamic graph convolutional networks for rumor detection on social media[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2022: 4611-4619.
[32] HAN S, YU K, SU X, et al. Combining temporal and interactive features for rumor detection: a graph neural network based model[J]. Neural Processing Letters, 2023, 55(5): 5675-5691.