Open AccessWhat reflects investor sentiment? Empirical evidence from China
Author(s) -
Zimei Huang,
Zhenghui Li
Publication year - 2021
Publication title -
data science in finance and economics
Language(s) - English
Resource type - Journals
ISSN - 2769-2140
DOI - 10.3934/dsfe.2021013
Subject(s) - index (typography) , volatility (finance) , stock market , sentiment analysis , stock market index , stock (firearms) , perspective (graphical) , econometrics , financial economics , correlation , economics , computer science , mathematics , artificial intelligence , geography , context (archaeology) , geometry , archaeology , world wide web
Investor sentiment tends to show systemic bias on the market, and exerts a significant impact on future market fluctuations, which tends to form an amplified feedback effect. This paper selects three different types of data, namely the emotional text data, the volatility of the stock price and the turnover rate, and other multi-index comprehensive data. Then, this paper formulates different types of investor sentiment indexes through different types of data. From fitting effect of three different types investor sentiment, three different types of investor sentiment index and stock price index correlation to compare the reliability of investor sentiment index. The findings are as follows: First, from the perspective of model fitting, the emotional text-based sentiment index performs better and the model is more robust. Second, from the perspective of market correlation, the text-based sentiment index has the strongest correlation with the stock market. Based on these, the investor sentiment index compiled based on emotional text data more fully reflects investor sentiment.