| Issue |
E3S Web Conf.
Volume 214, 2020
2020 International Conference on Energy Big Data and Low-carbon Development Management (EBLDM 2020)
|
|
|---|---|---|
| Article Number | 03001 | |
| Number of page(s) | 11 | |
| Section | Digital Development and Environmental Management of Energy Supply Chain | |
| DOI | https://doi.org/10.1051/e3sconf/202021403001 | |
| Published online | 07 December 2020 | |
Related Research on News Sentiment Tendency and Stock Price Fluctuation
Department of Software Engineering, Southeast University, Nanjing, China
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.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.