Investors’ opinion divergence and stock return volatility: evidence from user-generated content

This paper examines the relationship between investors’ opinion divergence and stock return volatility using daily UGC data of 66 most discussed stocks from one of the most popular social media platforms for investors in the USA. Specifically, we use an unsupervised learning method to measure opinion divergence and apply both dynamic panel regression and panel vector autoregressive regression (pVAR) to explore its role in return volatility. We find that investors’ opinion divergence is negatively associated with future return volatility across a variety of holding periods. Moreover, the impact of opinion divergence will become attenuated over time. Our research adds to the emerging body of literature on the impact of UGC on the stock market regarding: 1) novel techniques for systematically measuring sentiment divergence in large-scale UGC data; 2) uncovering the dynamic interdependence of the relationship between investors’ opinion divergence and stock return volatility.