Emotion contagion and stock market: the role of online investor network in China

Social media serves as a crucial channel for investors to acquire asset-related information while also facilitating emotional contagion through social connections. However, the association between the emotional contagion on social networks and asset prices remains unclear. We examine the relationship between market returns and disseminated emotion resulting from emotion contagion in a social network of more than 2.5 million investors in a finance-specific forum. Investors' emotions are detected from their short-text posts based on a novel classification framework that leverages the traditional dictionary-based method and the Bidirectional Encoder Representations from Transformers (BERT). The potential of investors in emotional contagion is approximated in terms of a global metric of Collective Influence measured daily from a large-scale social network. We find that disseminated emotion is negatively associated with next-day returns, highlighting the importance of the network effect in reshaping the process of investors' emotional contagion and subsequently influencing asset prices. Our findings suggest that understanding and monitoring emotional contagion in social networks can aid in predicting market movements, and policymakers can leverage these insights to enhance market stability by addressing investors' psychological and social aspects.