Abstract
The purpose of this research is to examine the impact of sentiment derived from news headlines on the direction of stock price changes. The study examines stocks listed on the WIG-banking sub-sector index on the Warsaw Stock Exchange. Two types of data were used: textual and market data. The research period covers the years 2015–2018. Through the research, 7,074 observations were investigated, of which 3,390 with positive sentiment, 2,665 neutral, and 1,019 negative. In order to examine the predictive power of sentiment, six machine learning models were used: Decision Tree Classifier, Random Forest Classifier, XGBoost Classifier, KNN Classifier, SVC and Gaussian Naive Bayes Classifier. Empirical results show that the sentiment of news headlines has no significant explanatory power for the direction of stock price changes in one-day time frame.
Subject
General Earth and Planetary Sciences
Reference41 articles.
1. 1. Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2, 1-8. https://doi.org/10.1016/j.jocs.2010.12.007
2. 2. Cawley, G.C., & Talbot, N.L. (2010). On over-fitting in model selection and subsequent selection bias in performance evaluation. Journal of Machine Learning Research, 11, 2079-2107.
3. 3. Charles, A., Darné, O., & Kim, J.H. (2012). Exchange-rate return predictability and the adaptive markets hypothesis: Evidence from major foreign exchange rates. Journal of International Money and Finance, 31, 1607-1626. https://doi.org/10.1016/j.jimonfin.2012.03.003
4. 4. Chatrath, A., Miao, H., Ramchander, S., & Villupuram, S. (2014). Currency jumps, cojumps and the role of macro news. Journal of International Money and Finance, 40, 42-62. https://doi.org/10.1016/j.jimonfin.2013.08.018
5. The behavior of stock-market prices;Fama;The Journal of Business,1965