- 期刊
Stock Forecasting: A Technique Combining Sentiment Analysis and Deep Learning
摘要
Financial markets are critical to the development of modern society. They enable the allocation of economic resources. However, forecasting the stock market has always been complicated. With the growth of various social media platforms and the advancement of natural language processing technology, academics have attempted to analyse textual data via mood or event extraction. However, there is a shortage of study on individual stock price increases compared to the general market trend. This work aims to investigate the deep Learning model for forecasting the price of ten stocks using financial news headlines. Numerous sentiment analysis tools, such as OpenIE and LSTM, are utilised to extract and model news events.
參考文獻
E. F. Fama, (1965) The behaviour of stock-market prices. J. Bus., vol. 38, no. 1, pp. 34–105.
Markowitz H, (1952) Portfolio selection[J]. The journal of finance, vol. 7, no. 1, pp. 77-91.
Makrehchi, S. Shah, and W. Liao, (2013) “Stock prediction using event-based sentiment analysis,” in Proc. IEEE/WIC/ACM Int. Joint Conf. Web Intell. (WI) Intell. Agent Technol. (IAT), vol. 1, pp. 337–342.
Bollen, H. Mao, and X. Zeng, (2011) Twitter mood predicts the stock market. J. Comput. Sci., vol. 2, no. 1, pp. 1–8.
Fung, G.P., Yu, J.X., & Lam, W, (2003) Stock prediction: Integrating text mining approach using real-time news. 2003 IEEE International Conference on Computational Intelligence for Financial Engineering, 2003. Proceedings., pp. 395-402.