Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning

TL;DR

This paper introduces an adversarial contrastive learning framework that effectively detects rumors in low-resource microblog domains by leveraging well-resourced data, domain adaptation, and adversarial augmentation, outperforming existing methods.

Contribution

The paper presents a novel adversarial contrastive learning approach with language alignment and augmentation to improve rumor detection in low-resource, multilingual, and unseen event scenarios.

Findings

Outperforms state-of-the-art rumor detection methods on low-resource datasets.

Effectively adapts features across different languages and domains.

Enhances early-stage rumor detection accuracy.

Abstract

Massive false rumors emerging along with breaking news or trending topics severely hinder the truth. Existing rumor detection approaches achieve promising performance on the yesterday's news, since there is enough corpus collected from the same domain for model training. However, they are poor at detecting rumors about unforeseen events especially those propagated in different languages due to the lack of training data and prior knowledge (i.e., low-resource regimes). In this paper, we propose an adversarial contrastive learning framework to detect rumors by adapting the features learned from well-resourced rumor data to that of the low-resourced. Our model explicitly overcomes the restriction of domain and/or language usage via language alignment and a novel supervised contrastive training paradigm. Moreover, we develop an adversarial augmentation mechanism to further enhance the robustness of low-resource rumor representation. Extensive experiments conducted on two low-resource datasets collected from real-world microblog platforms demonstrate that our framework achieves much better performance than state-of-the-art methods and exhibits a superior capacity for detecting rumors at early stages.