A novel stock evaluation index based on public opinion analysis

In recent years, researches on sentiment of individual investors are becoming popular, especially using big data technology. Most researches mainly focus on the relationship between the individual sentiment and the market fluctuations. In this work, we aim to testify the time-sensitivity of stock prices against the general sentiment of individual investors and to assess the influence of the evaluation of consulting institutions on stock prices. Firstly, we develop a distributed web spider to fetch the opinions data from social networks like Sina Guba, Eastmoney Guba and Sina Finance, and financial data from the RESSET database. Then through natural language processing, we build a sentiment index and institution evaluation index. Finally, we use correlation analysis, regression analysis and time series analysis to achieve our targets. The results show that: 1) the fluctuation of stock prices is more sensitively to the intraday sentiment of individuals; 2) there is no significant correlation between general sentiment of individual investors and the evaluation of consulting institutions, though the two factors both surely influence the change of stock prices; 3) the change of stock prices can be expressed by the public opinion well.