LSTM-based sentiment analysis for stock price forecast

• Published in: PeerJ. Computer science Vol. 7; p. e408
• Main Authors: Ko, Ching-Ru, Chang, Hsien-Tsung
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 11.03.2021; PeerJ, Inc; PeerJ Inc
• Subjects: Artificial Intelligence; BERT; Central banks; Computational linguistics; Data mining; Data Science; Deep learning; Efficient markets; Emerging Technologies; Financial management; Forecasts and trends; Hypotheses; Investments; Language processing; LSTM neural network; Memory; Natural language interfaces; Natural language processing; Neural networks; Prices; Prices and rates; Pricing; Random walk theory; Root-mean-square errors; Securities industry; Securities markets; Sentiment analysis; Social networks; Stock exchanges; Stock price forecast; Stocks; Text sentiment analysis; Time series; Trends; China; Taiwan; Stock price forecast; BERT; Text sentiment analysis; LSTM neural network
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/peerj-cs.408

Investing in stocks is an important tool for modern people’s financial management, and how to forecast stock prices has become an important issue. In recent years, deep learning methods have successfully solved many forecast problems. In this paper, we utilized multiple factors for the stock price forecast. The news articles and PTT forum discussions are taken as the fundamental analysis, and the stock historical transaction information is treated as technical analysis. The state-of-the-art natural language processing tool BERT are used to recognize the sentiments of text, and the long short term memory neural network (LSTM), which is good at analyzing time series data, is applied to forecast the stock price with stock historical transaction information and text sentiments. According to experimental results using our proposed models, the average root mean square error (RMSE ) has 12.05 accuracy improvement.