Using financial news sentiment for stock price direction prediction

Fazlija, Bledar; Harder, Pedro

doi:10.3390/math10132156

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-25471

Publication type:	Article in scientific journal
Type of review:	Peer review (publication)
Title:	Using financial news sentiment for stock price direction prediction
Authors:	Fazlija, Bledar Harder, Pedro
et. al:	No
DOI:	10.3390/math10132156 10.21256/zhaw-25471
Published in:	Mathematics
Volume(Issue):	10
Issue:	13
Page(s):	2156
Issue Date:	2022
Publisher / Ed. Institution:	MDPI
ISSN:	2227-7390
Language:	English
Subjects:	Machine learning; Natural language processing; Sentiment analysis; Stock price prediction
Subject (DDC):	006: Special computer methods 332: Financial economics
Abstract:	Using sentiment information in the analysis of financial markets has attracted much attention. Natural language processing methods can be used to extract market sentiment information from texts such as news articles. The objective of this paper is to extract financial market sentiment information from news articles and use the estimated sentiment scores to predict the price direction of the stock market index Standard & Poor’s 500. To achieve the best possible performance in sentiment classification, state-of-the-art bidirectional encoder representations from transformers (BERT) models are used. The pretrained transformer networks are fine-tuned on a labeled financial text dataset and applied to news articles from known providers of financial news content to predict their sentiment scores. The generated sentiment scores for the titles of the given news articles, for the (text) content of said news articles, and for the combined title-content consideration are posited against past time series information of the stock market index. To forecast the price direction of the stock market index, the predicted sentiment scores are used in a simple strategy and as features for a random forest classifier. The results show that sentiment scores based on news content are particularly useful for stock price direction prediction.
URI:	https://digitalcollection.zhaw.ch/handle/11475/25471
Fulltext version:	Published version
License (according to publishing contract):	CC BY 4.0: Attribution 4.0 International
Departement:	School of Management and Law
Organisational Unit:	Institute of Wealth & Asset Management (IWA)
Appears in collections:	Publikationen School of Management and Law

Files in This Item:

File	Description	Size	Format
2022_Fazlija-Harder_Using-financial-news-sentiment-stock-price-direction-prediction.pdf		2.8 MB	Adobe PDF	View/Open

Show full item record

Fazlija, B., & Harder, P. (2022). Using financial news sentiment for stock price direction prediction. Mathematics, 10(13), 2156. https://doi.org/10.3390/math10132156

Fazlija, B. and Harder, P. (2022) ‘Using financial news sentiment for stock price direction prediction’, Mathematics, 10(13), p. 2156. Available at: https://doi.org/10.3390/math10132156.

B. Fazlija and P. Harder, “Using financial news sentiment for stock price direction prediction,” Mathematics, vol. 10, no. 13, p. 2156, 2022, doi: 10.3390/math10132156.

FAZLIJA, Bledar und Pedro HARDER, 2022. Using financial news sentiment for stock price direction prediction. Mathematics. 2022. Bd. 10, Nr. 13, S. 2156. DOI 10.3390/math10132156

Fazlija, Bledar, and Pedro Harder. 2022. “Using Financial News Sentiment for Stock Price Direction Prediction.” Mathematics 10 (13): 2156. https://doi.org/10.3390/math10132156.

Fazlija, Bledar, and Pedro Harder. “Using Financial News Sentiment for Stock Price Direction Prediction.” Mathematics, vol. 10, no. 13, 2022, p. 2156, https://doi.org/10.3390/math10132156.