A Study of Relationship between Investor Sentiment and Stock Price : Realization of Investor Sentiment Classification Based on Bayesian Model

The effectiveness of China’s stock market is low, and the degree of information disclosure is worse than that of capital markets in developed countries. In particular, GEM stocks are slow to reflect basic supply and demand factors, and investor sentiment will have an impact on GEM stock prices. This paper selects the historical posting data of “GEM Finger Bar” of Eastmoney website. Firstly, Bayesian model algorithm is used to classify the sentiment of text comments, and investor sentiment proxy variables are constructed. Then, through correlation analysis and Granger causality test, the relationship between investor sentiment and the GEM stock price in China is empirically studied. The results show that there is a strong correlation between GEM stock prices and investor sentiment.