Check-worthy Claim Detection across Topics for Automated Fact-checking

TL;DR

This paper addresses the challenge of detecting check-worthy claims across diverse topics in automated fact-checking, proposing a novel model that improves performance on unseen topics through few-shot learning and data augmentation.

Contribution

The paper introduces the AraCWA model, which enhances cross-topic claim detection by incorporating few-shot learning and data augmentation strategies.

Findings

Data augmentation significantly improves performance across topics.

Semantic similarity between topics correlates with detection difficulty.

AraCWA outperforms baseline models on Arabic tweet dataset.

Abstract

An important component of an automated fact-checking system is the claim check-worthiness detection system, which ranks sentences by prioritising them based on their need to be checked. Despite a body of research tackling the task, previous research has overlooked the challenging nature of identifying check-worthy claims across different topics. In this paper, we assess and quantify the challenge of detecting check-worthy claims for new, unseen topics. After highlighting the problem, we propose the AraCWA model to mitigate the performance deterioration when detecting check-worthy claims across topics. The AraCWA model enables boosting the performance for new topics by incorporating two components for few-shot learning and data augmentation. Using a publicly available dataset of Arabic tweets consisting of 14 different topics, we demonstrate that our proposed data augmentation strategy achieves substantial improvements across topics overall, where the extent of the improvement varies across topics. Further, we analyse the semantic similarities between topics, suggesting that the similarity metric could be used as a proxy to determine the difficulty level of an unseen topic prior to undertaking the task of labelling the underlying sentences.