Emotion-Drive Interpretable Fake News Detection

Abstract

Fake news has brought significant challenges to the healthy development of social media. Although current fake news detection methods are advanced, many models directly utilize unselected user comments and do not consider the emotional connection between news content and user comments. The authors propose an emotion-driven explainable fake news detection model (EDI) to solve this problem. The model can select valuable user comments by using sentiment value, obtain the emotional correlation representation between news content and user comments by using collaborative annotation, and obtain the weighted representation of user comments by using the attention mechanism. Experimental results on Twitter and Weibo show that the detection model significantly outperforms the state-of-the-art models and provides reasonable interpretation.