Fake News, Real Emotions: Emotion Analysis of COVID-19 Infodemic in Weibo

The proliferation of COVID-19 fake news on social media poses a severe threat to the health information ecosystem. We show that affective computing can make significant contributions to combat this infodemic. Given that fake news is often presented with emotional appeals, we propose a new perspective on the role of emotion in the attitudes, perceptions, and behaviors of the dissemination of information. We study emotions in conjunction with fake news, and explore different aspects of their interaction. To process both emotion and ‘falsehood’ based on the same set of data, we auto-tag emotions on existing COVID-19 fake news datasets following an established emotion taxonomy. More specifically, based on the distribution of seven basic emotions (e.g. Happiness, Like, Fear, Sadness, Surprise, Disgust, Anger), we find across domains and styles that COVID-19 fake news is dominated by emotions of Fear (e.g., of coronavirus), and Disgust (e.g., of social conflicts). In addition, the framing of fake news in terms of gain-versus-loss reveals a close correlation between emotions, perceptions, and collective human reactions. Our analysis confirms the significant role of emotion Fear in the spreading of the fake news, especially when contextualized in the loss frame. Our study points to a future direction of incorporating emotion footprints in models of automatic fake news detection, and establishes an affective computing approach to information quality in general and fake news detection in particular.