Related Research on News Sentiment Tendency and Stock Price Fluctuation

• Published in: E3S Web of Conferences Vol. 214; p. 3001
• Main Author: Li, Hongye
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Les Ulis EDP Sciences 01.01.2020
• Subjects: Artificial intelligence; Artificial neural networks; Asset pricing; Internet; Investment policy; Investment strategy; Investments; Model accuracy; Neural networks; News
• ISSN: 2267-1242; 2555-0403; 2267-1242
• DOI: 10.1051/e3sconf/202021403001

In recent years, with further development of the Internet and artificial intelligence, the research on using news sentiments, and then predicting investor behavior has become more feasible. Based on the news information obtained from the Internet, this article analyzes the investor ‘s emotions about the news, further predicts the behavior of investors, and then the rise and fall of investment asset prices. We use news sentiment tendency and stock price of listed companies to analyze whether the news sentiment really affects the stock price and the degree of its influence. The research results of the thesis are divided into two parts: (1) A CNN neural network capable of analyzing news that may have an impact on stock prices in the near future is designed and trained to obtain a timely response and form a simulated investment decision for investors to adjust the investment strategy timely; (2) Combined with the economic indicators, this article uses the LSTM neural network to comprehensively investigate whether the emotional tendency of the news has a significant impact on the stock price. This article draws four kinds of images, which can test the accuracy of the model from different angles and guide consumers’ investment.