How the individual investors took on big data: The effect of panic from the internet stock message boards on stock price crash

Abstract

This study examines whether the sentiments expressed in the stock forum posted by individual investors lead to abnormal trading and impose a significant impact on stock price crashes. The history of world financial crises reveals that investor panic is one of the most important factors triggering market crashes. In this paper, we propose a measure to estimate investor panic and its effect on a stock price crash. Using Growth Enterprise Market firms in China's Shenzhen Stock Exchange as a sample, we utilize a computer text mining tool to analyze the contents of nearly one million posts from the largest Chinese stock message board. According to the posting contents, we built a daily Sentiment Index and a Panic Index at the firm level. The empirical results show that the high Sentiment Index leads to a significant following abnormal trading. After controlling public information announcements, this effect is still significant. Moreover, the Panic Index could predict the stock price crash. The effect of the Panic Index on the price crash is stronger either when the information disclosure is opaque or when the proportion of shares held by institutional investors is low.