Meet The Truth: Leverage Objective Facts and Subjective Views for Interpretable Rumor Detection

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 705–715 August 1–6, 2021. ©2021 Association for Computational Linguistics 705 Meet The Truth: Leverage Objective Facts and Subjective Views for Interpretable Rumor Detection Jiawen Li, Shiwen Ni and Hung-Yu Kao Intelligent Knowledge Management Lab Department of Computer Science and Information Engineering National Cheng Kung University Tainan, Taiwan {P78073012,P78083033}@gs.ncku.edu.tw,hykao@mail.ncku.edu.tw Abstract Existing rumor detection strategies typically provide detection labels while ignoring their explanation. Nonetheless, providing pieces of evidence to explain why a suspicious tweet is rumor is essential. As such, a novel model, LOSIRD, was proposed in this paper. First, LOSIRD mines appropriate evidence sentences and classifies them by automatically checking the veracity of the relationship of the given claim and its evidence from about 5 million Wikipedia documents. LOSIRD then automatically constructs two heteroge- neous graph objects to simulate the propaga- tion layout of the tweets and code the rela- tionship of evidence. Finally, a graphSAGE processing component is used in LOSIRD to provide the label and evidence. To the best of our knowledge, we are the first one who combines objective facts and subjective views to verify rumor. The experimental results on two real-world Twitter datasets showed that our model exhibited the best performance in the early rumor detection task and its rumor de- tection performance outperformed other base- line and state-of-the-art models. Moreover, we confirmed that both objective information and subjective information are fundamental clues for rumor detection. 1 Introduction With the prevalence of social media platforms, ru- mors have been a serious social problem. Notably, existing rumor detection methods roughly formu- late this task as a natural language classification task. The goal of the task is to simply label a given textual claim as rumor or non-rumor. Nevertheless, only a verdict to a suspicious statement is insuffi- cient for people to understand and reason why a claim is a rumor. For example, Fig.1 is the com- parison figure of existing rumor detection methods and a rumor detection method that provides evi- dence. The claim in Fig. 1 is a half-truth, which Figure 1: Comparison figure of rumor detection re- sults of two different systems. The orange highlights in Fig.1 (b) are pieces of evidence retrieved from Wikipedia. From those evidence sentences, readers can easily judge if the given claim is a half-truth and clearly understand why that claim is a rumor. is highly deceptive. For such rumors, providing a label only is unconvincing. Thus, we believe that a good rumor detection system should have 2 essential functions including, a rumor identifying function and evidence providing function. Rumor detection that provides evidence has the following benefits: (1) Improve detection perfor- mance. (2) Improve the user experience. (3) Pro- vide a basis for manual review. (4) Improve the accuracy of early rumor detection. (5) Intercept the spread of similar rumors. Despite having numerous advantages, rumor de- tection that provides evidence is extremely hard. If none of the labeled evidence information is in- cluded in a rumor detection training dataset, the …

Content truncated to 500 words