Contrastive Learning at the Relation and Event Level for Rumor Detection

Existing studies for rumor detection rely heavily on a large number of labeled data to operate in a fully-supervised manner. However, manual data annotation in realistic cases is very expensive and time-consuming. In this paper, we propose a novel self-supervised Relation-Event based Contrastive Lea...

Full description

Saved in:
Bibliographic Details
Main Authors: Xu, Yingrui, Hu, Jingyuan, Ge, Jingguo, Wu, Yulei, Li, Tong, Li, Hui
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
Annotations
contrastive learning
Data models
graph neural networks
Manuals
Rumor detection
self-supervised learning
Semantics
Signal processing
Task analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Existing studies for rumor detection rely heavily on a large number of labeled data to operate in a fully-supervised manner. However, manual data annotation in realistic cases is very expensive and time-consuming. In this paper, we propose a novel self-supervised Relation-Event based Contrastive Learning (RECL) framework for rumor detection to address the above issue. Specifically, we present both the relation-level and event-level augmentation strategies to generate contrastive samples, which capture both the semantics revealed by repost relations and the structural features of rumor events. Moreover, contrastive learning tasks are devised to generate informative graph representations by utilizing self-supervision signals of unlabeled data. Extensive experimental results on real-world datasets demonstrate the effectiveness of our model, especially with limited labeled data.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10096567