Modeling Evolution of Message Interaction for Rumor Resolution

Proceedings of the 28th International Conference on Computational Linguistics, pages 6377–6387 Barcelona, Spain (Online), December 8-13, 2020 6377 Modeling Evolution of Message Interaction for Rumor Resolution Lei Chen1, Zhongyu Wei1,2∗, Jing Li3, Baohua Zhou4, Qi Zhang5, Xuanjing Huang5 1 School of Data Science, Fudan University, China 2 Research Institute of Intelligent and Complex Systems, Fudan University, China 3 Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China 4 School of Journalism, Fudan University, China 5 School of Computer Science, Fudan University, China 1,2,5{chenl18,zywei,qi zhang,xjhuang}@fudan.edu.cn 3jing-amelia.li@polyu.edu.hk; 4zhoubaohua@yeah.net Abstract Previous work for rumor resolution concentrates on exploiting time-series characteristics or mod- eling topology structure separately. However, how local interactive pattern affects global infor- mation assemblage has not been explored. In this paper, we attempt to address the problem by learning evolution of message interaction. We model confrontation and reciprocity between mes- sage pairs via discrete variational autoencoders which effectively reflects the diversified opinion interactivity. Moreover, we capture the variation of message interaction using a hierarchical framework to better integrate information flow of a rumor cascade. Experiments on PHEME dataset demonstrate our proposed model achieves higher accuracy than existing methods. 1 Introduction With increasing openness of social media platforms, unverified messages can be easily disseminated from person to person and result in tremendous rumor cascades which expose huge threat to individuals and society. To resolve rumors, firstly we need to detect statements that are ambiguous at the time of posting, then explore how users share and discuss rumors and finally assess their veracity as true, false or unverified. This can be represented as a pipeline of sub-tasks, including rumor detection, stance classification and rumor verification (Zubiaga et al., 2018a). Identifying and debunking rumors automatically has been extensively studied in the past few years. State-of-the-art approaches construct sequential representations following a chronological order and then utilize temporal features to capture dynamic signals (Zubiaga et al., 2016; Ma et al., 2016; Wei et al., 2019). Although the source content stays invariable, time-series modeling successfully locates modifiers who might import evidence to correct misinformation or stir up enmity to discredit truth (Zhang et al., 2013). These models generate promising results, however, they ignore local interactions happened during the message diffusion which is deemed to be important for the identification of rumors. Figure 1 (a) shows a rumor cascade which is identified as false for devilishly suspect Ray Radley’s role in the appalling Sydney siege. As can be seen, denial to false rumor tends to evoke affirmative replies which further confuses the factuality of the message. Besides, disagreement and query towards descrip- tive statements are able to trigger drastic discussion and result in validity modification. Although some researchers explore propagation structure of rumor proliferation (Ma et al., 2017; Kumar and Carley, 2019), they typically rely on rough aggregation of locally successional messages. Moreover, the evolution of message interaction depicts the global characteristic of rumor cascades which improves the performance of verification. Figure 1 (b) illustrates the intuition using statistics drawn from PHEME dataset (Kochkina et …

Content truncated to 500 words