An Emotion-Aware Approach for Fake News Detection

Social media has gradually become the main medium for news transmission. Rumors and real information are mixed on social platforms, which will have certain impact on social order and public psychology. To solve this problem, many fake news detection models based on content and propagation path have been proposed. However, most previous methods do not consider the emotional information contained in the news. Therefore, we propose a novel framework for detecting fake news, which leverages graph neural network to jointly model the content, emotional information and propagation structure of news conversations. Also, in order to use emotion to amplify the spread of fake news, we propose an edge-aware method to enhance the news graph representation. The experimental results indicate that our model achieves state-of-the-art performance on various fake news detection tasks.