Emotion-Drive Interpretable Fake News Detection

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