Publication Type

Journal Article

Version

publishedVersion

Publication Date

4-2024

Abstract

Rumor verification on social media aims to identify the truth value of a rumor, which is important to decreasethe detrimental public effects. A rumor might arouse heated discussions and replies, conveying differentstances of users that could be helpful in identifying the rumor. Thus, several works have been proposedto verify a rumor by modelling its entire stance sequence in the time domain. However, these works ignorethat such a stance sequence could be decomposed into controversies with different intensities, which could beused to cluster the stance sequences with the same consensus. In addition, the existing stance extractors fail toconsider both the impact of all previously posted tweets and the reply chain on obtaining the stance of a newreply. To address the above problems, in this article, we propose a novel stance-based network to aggregatethe controversies of the stance sequence for rumor verification, termed Filter-based Stance Network (FSNet).As controversies with different intensities are reflected as the different changes of stances, it is convenient torepresent different controversies in the frequency domain, but it is hard in the time domain. Our proposedFSNet decomposes the stance sequence into multiple controversies in the frequency domain and obtainsthe weighted aggregation of them. Specifically, FSNet consists of two modules: the stance extractor and thefilter block. To obtain better stance features toward the source, the stance extractor contains two stages.In the first stage, the tweet representation of each reply is obtained by aggregating information from allpreviously posted tweets in a conversation. Then, the features of stance toward the source, i.e., rumor-awarestance, are extracted with the reply chains in the second stage. In the filter block module, a rumor-awarestance sequence is constructed by sorting all the tweets of a conversation in chronological order. FourierTransform thereafter is employed to convert the stance sequence into the frequency domain, where differentfrequency components reflect controversies of different intensities. Finally, a frequency filter is applied toexplore the different contributions of controversies. We supervise our FSNet with both stance labels andrumor labels to strengthen the relations between rumor veracity and crowd stances. Extensive experimentson two benchmark datasets demonstrate that our model substantially outperforms all the baselines.

Keywords

Social media, frequency filter, rumor verification, rumor-aware stance

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

ACM Transactions on Information Systems

Volume

42

Issue

4

First Page

1

Last Page

28

ISSN

1046-8188

Identifier

10.1145/3649462

Publisher

Association for Computing Machinery (ACM)

Download

Share

COinS