•  
  •  
 

ORCID

Kamil Polak 0000-0002-9897-8431

Keywords

sentiment analysis; natural language processing; machine learning; financial forecasting; behavioral finance

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.

First Page

72

Last Page

90

Page Count

90

Received Date

13 September 2021

Revised Date

8 December 2021

Accept Date

18 December 2021

Online Available Date

30 December 2021

DOI

10.7172/2353-6845.jbfe.2021.2.4

JEL Code

G14; G17; G41

Publisher

University of Warsaw

Share

COinS