The Influence of Online News on Thai Investors' Stock Investment Decisions

Phum Tanggasemsun; Pariyada Sukcharoensin

Authors

Phum Tanggasemsun Beryl 8 Plus Company Limited
Pariyada Sukcharoensin National Institute of Development Administration

Keywords:

Conventional online behavior, National Language Processing, Sentiment, Time lag, Trend

Abstract

In this study, we explore the sentiment of publicly available financial news from online sources related to stocks in the Thai stock exchange markets, along with other relevant factors. The multiple datasets are gathered from economic and financial news across the internet during the easing period of COVID-19 restrictions. Sentiment is defined using Natural Language Processing (NLP) techniques, which analyze headlines with wordlists. We implement data mining and data analysis techniques in the financial field to enhance data gathering and processing. The advantages of this technological approach include repeatability, reliability over time, and the ability to handle large datasets. Conventional online behavior, such as trends, is included as a complementary variable alongside sentiment. Stock characteristics, including index, industrial category, and market, are included as sub-independent variables. The empirical results indicate that sentiment, trends, and other factors are related to stock movement, with magnitudes of each variable varying according to time differences.

References

Chatchawan, S. (2021). Can sentiment from news headlines explain stock market returns?: Evidence from Thailand. Thammasat Review, 24(1), 317-333.

Chatchawan, S. (2022). How does news-based sentiment affect stock market volatility in the Stock Exchange of Thailand? KKBS Journal of Business Administration and Accountancy, 5(3), 161-182.

Chiewhawan, T., & Vateekul, P. (2020). Explainable deep learning for Thai stock market prediction using textual representation and technical indicators. In Proceedings of the 8th International Conference on Computer and Communications Management (pp. 19-23).

Liu, L., Wu, J., Li, P., & Li, Q. (2015). A social-media-based approach to predicting stock comovement. Expert Systems with Applications, 42(8), 3893-3901.

Luo, X., Zhang, J., & Duan, W. (2013). Social media and firm equity value. Information Systems Research, 24(1), 146-163.

Nguyen, T. H., Shirai, K., & Velcin, J. (2015). Sentiment analysis on social media for stock movement prediction. Expert Systems with Applications, 42(24), 9603-9611.

Si, J., Mukherjee, A., Liu, B., Li, Q., Li, H., & Deng, X. (2013). Exploiting topic based Twitter sentiment for stock prediction. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (pp. 24-29).

Sul, H. K., Dennis, A. R., & Yuan, L. I. (2016). Trading on Twitter: Using social media sentiment to predict stock returns. Decision Sciences, 48(3), 454-488.

Tu, W., Cheung, D. W., Mamoulis, N., Yang, M., & Lu, Z. (2016). Investment recommendation using investor opinions in social media. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval (pp. 881-884).

Vu, T., Chang, S., Ha, Q. T., & Collier, N. (2012). An experiment in integrating sentiment features for tech stock prediction in Twitter. In Proceedings of the Workshop on Information Extraction and Entity Analytics on Social Media Data (pp. 23-38).

Wansri, T., Phaksuwan, A., Iamtae, K., & Chaturantabut, S. (2023). Prediction models for tourism stock market trends during COVID-19 pandemic using news sentiment analysis with data mining: A case study. Science and Technology Asia, 28(3), 98-115.