Leveraging Commonsense Knowledge on Classifying False News and Determining Checkworthiness of Claims
This addresses the problem of time-consuming manual fact-checking for combating false news, but it is incremental as it builds on existing BERT models.
The paper tackles automated fact-checking by leveraging commonsense knowledge to improve false news classification and check-worthy claim detection, showing performance gains in experiments on public and new datasets.
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.