Coupled Hierarchical Transformer for Stance-Aware Rumor Verification in Social Media Conversations

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 1392–1401, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 1392 Coupled Hierarchical Transformer for Stance-Aware Rumor Verification in Social Media Conversations Jianfei Yu1, Jing Jiang2, Ling Min Serena Khoo3, Hai Leong Chieu3, and Rui Xia1 1 School of Artificial Intelligence, Nanjing University of Science & Technology, China 2 School of Information Systems, Singapore Management University, Singapore 3 DSO National Laboratories, Singapore {jfyu, rxia}@njust.edu.cn, jingjiang@smu.edu.sg, {klingmin, chaileon}@dso.org.sg Abstract The prevalent use of social media enables rapid spread of rumors on a massive scale, which leads to the emerging need of automatic rumor verification (RV). A number of previ- ous studies focus on leveraging stance classi- fication to enhance RV with multi-task learn- ing (MTL) methods. However, most of these methods failed to employ pre-trained contex- tualized embeddings such as BERT, and did not exploit inter-task dependencies by using predicted stance labels to improve the RV task. Therefore, in this paper, to extend BERT to obtain thread representations, we first pro- pose a Hierarchical Transformer1, which di- vides each long thread into shorter subthreads, and employs BERT to separately represent each subthread, followed by a global Trans- former layer to encode all the subthreads. We further propose a Coupled Transformer Mod- ule to capture the inter-task interactions and a Post-Level Attention layer to use the pre- dicted stance labels for RV, respectively. Ex- periments on two benchmark datasets show the superiority of our Coupled Hierarchical Trans- former model over existing MTL approaches. 1 Background Recent years have witnessed a profound revolu- tion in social media, as many individuals gradually turn to different social platforms to share the latest news and voice personal opinions. Meanwhile, the flourish of social media also enables rapid dissemi- nation of unverified information (i.e., rumors) on a massive scale, which may cause serious harm to our society (e.g., impacting presidential election decisions (Allcott and Gentzkow, 2017)). Since manually checking a sheer quantity of rumors on 1Note that the concept of hierarchy in this paper is different from that in Yang et al. (2016), as we use hierarchy to refer to a neural structure that first models the local interactions among posts within each subthread, followed by modeling the global interactions among all the posts in the whole thread. Lee Kuan Yew died already. www.pmo.gov.sg/lky. Source Post Query Is it true? Lee Kuan Yew Died? Can anyone confirm it? No, I don’t believe it is true. R2: Reply Post R21: Reply Post Deny Support He died several days ago. They didn’t announce until now. R1: Reply Post I also think so. He was on TV last week. R211: Reply Post Deny Support Stance Label Veracity Label: False Rumor Figure 1: An example conversation thread with both rumor veracity label and stance labels. Each post has a stance label towards the claim in the source post, and the source claim was later identified as false rumor. social media is naturally labor-intensive and time- consuming, it is crucial …

Content truncated to 500 words