Open AccessMachine Learning and Artificial Intelligence Applied in the Research of the Emotions Impact on Forecasting
Author(s) -
Yaokui Jiang,
Yi Zuo,
Yudong Yang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1982/1/012052
Subject(s) - sentiment analysis , granger causality , composite index , stock market , index (typography) , econometrics , stock (firearms) , stock market index , computer science , database transaction , capital market , artificial intelligence , economics , financial economics , stock exchange , finance , engineering , world wide web , mechanical engineering , paleontology , horse , biology , programming language
According to the behavioral finance theory, the psychology and behavior of investors in capital market have an important impact on the fluctuation of stock index. Therefore, this paper assumes that there is a certain internal mechanism between investor sentiment and stock index, which can predict the overall price change of the stock market. The text mining technology and sentiment analysis method can be used to generate a total of six categorypositive and negativeinvestor sentiment time series data, with three orders; The methods such as unit root test, Granger causality test and factor analysis are used to construct the composite index of SSE investor sentiment, and then the support vector machine and neural network are adopted to predict the stock market price changes and conduct the hypothesis verification. The results indicate that the SSE investor sentiment composite index constructed by using the text data of online stock market forum and stock transaction data can improve the accuracy of stock index trend prediction, which is conducive to better decision-making of the government, online platforms, listed companies, and investment entities.