Title: Thai stock news classification based on price changes and sentiments

Authors: Ponrudee Netisopakul; Woranun Saewong

Addresses: Faculty of Information Technology, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand ' Faculty of Information Technology, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand

Abstract: This research investigates the daily stock news influences toward a company's stock price direction in the Stock Exchange of Thailand. First, machine learning's text classification methods, namely, naïve Bayes, decision tree, random forest, support vector machine, and the three-layer and the five-layer backpropagation neural networks, are applied to predict the stock price directions using stock news collected during the year 2018. Then, the stock news sentiment is incorporated to help improve the prediction accuracy. Last, a meaningful grouping of stock news is carried out to further improve the direction prediction. The testing dataset collected from January to March 2019 stock news are used for model evaluations. The best accuracy obtained from the baseline dataset using stock news only is 78.6%. When dataset is augmented with sentiments and grouped, the best accuracy increases to 90.6%.

Keywords: stock prediction; stock news; machine learning; text classification; Stock Exchange of Thailand; SET; Thai language processing; natural language processing; sentiment analysis; clustering.

DOI: 10.1504/IJEF.2022.120360

International Journal of Electronic Finance, 2022 Vol.11 No.1, pp.49 - 66

Received: 01 Jun 2021
Accepted: 28 Sep 2021
Published online: 17 Jan 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article