Leveraging Commonsense Knowledge on Classifying False News and Determining Checkworthiness of Claims

TL;DR

This paper explores using commonsense knowledge to improve automated false news classification and claim checkworthiness detection by fine-tuning BERT with a multi-task learning approach, showing performance gains over existing models.

Contribution

It introduces a novel multi-task learning framework leveraging commonsense knowledge to enhance false news and claim detection accuracy.

Findings

Commonsense knowledge improves false news classification.

The proposed model outperforms single-task BERT models.

Enhanced detection of check-worthy claims achieved.

Abstract

Widespread and rapid dissemination of false news has made fact-checking an indispensable requirement. Given its time-consuming and labor-intensive nature, the task calls for an automated support to meet the demand. In this paper, we propose to leverage commonsense knowledge for the tasks of false news classification and check-worthy claim detection. Arguing that commonsense knowledge is a factor in human believability, we fine-tune the BERT language model with a commonsense question answering task and the aforementioned tasks in a multi-task learning environment. For predicting fine-grained false news types, we compare the proposed fine-tuned model's performance with the false news classification models on a public dataset as well as a newly collected dataset. We compare the model's performance with the single-task BERT model and a state-of-the-art check-worthy claim detection tool to evaluate the check-worthy claim detection. Our experimental analysis demonstrates that commonsense knowledge can improve performance in both tasks.