The Impact of Persian News on Stock Returns Through Text Mining Techniques

Document Type : Research Paper

Authors

Department of Management, Faculty of Social Sciences and Economics, Alzahra University, Tehran, Iran

Abstract

The news contains information about the fundamentals of the company and can change the behavior of the stock market. However, most research in stock market prediction has relied on technical analysis, i.e., time series analysis, based on past stock data, and the impact of fundamental data – especially Persian news – on the stock prices has been neglected. Consequently, this study aimed to fill this gap. To this aim, the stock index values were collected from the Tehran Stock Exchange along with the news published during this period. Then, the semantic load of news sentences was determined using text mining and sentiments analysis techniques, and the news was classified into positive and negative categories using machine-learning algorithms. Finally, the relationship between news and stock index was evaluated using logistic regression. According to the results, published news has a positive or negative semantic burden, and is effective on the index value.

Keywords

Main Subjects


Article Title [فارسی]

بررسی تأثیر اخبار فارسی بر بازدهی سهام با استفاده از تکنیک‌های متن‌کاوی

Authors [فارسی]

  • زهرا عزیزی
  • ندا عبدالوند
  • حسن قالیباف اصل
  • سعیده رجائی هرندی
کارشناسی ارشد مدیریت فناوری اطلاعات، گروه مدیریت، دانشکده علوم اجتماعی و اقتصادی، دانشگاه الزهرا
Abstract [فارسی]

اخبار حاوی اطلاعاتی درباره اصول بنیادی شرکت می‌باشند و می‌توانند رفتار بازار سهام را تغییر دهند. با این وجود، اغلب پژوهش‌های انجام‌شده در حوزه‌ پیش‌بینی بازارهای سهام متکی به تحلیل فنی، یعنی تحلیل سری‌های زمانی و مبتنی بر داده‌های گذشته‌ سهام بوده‌اند و تاثیر داده‎های بنیادی نادیده گرفته شده است.لذا، در این پژوهش با استفاده از رویکردهای متن‌کاوی و رگرسیون، بر اساس داده‌های فنی و بنیادی، به بررسی تأثیر اخبار بر شاخص سهام پرداخته شد. بدین‌منظور، ابتدا مقدار شاخص سهام در بازه زمانی معین از سازمان بورس اوراق بهادار تهران و اخبار منتشره در بازه زمانی مشابه، به‏طور خودکار از پایگاه خبری جمع‎آوری شد. سپس، با استفاده از تکنیک‌های متن‌کاوی و احساس‎کاوی به تعیین بار معنایی جمله‌های خبری پرداخته شد، و با استفاده از الگوریتم‌های یادگیری ماشین اخبار به دو دسته‌ی مثبت و منفی طبقه‌بندی شدند. در نهایت، با استفاده از رگرسیون رابطه‌ بین اخبار و شاخص سهام بررسی و دقت به‌دست‌آمده ارزیابی شد. با توجه به نتایج، هر خبر منتشرشده دارای بار معنایی مثبت یا منفی است، و علاوه بر اینکه مقدار شاخص از روند تاریخی خود پیروی می‌کند، از خبرهای منتشره که از نوع داده‌های بنیادی است، نیز تأثیر می‌پذیرد.

Keywords [فارسی]

  • شاخص بازار سهام
  • پیش‌بینی بازار سهام
  • اخبار فارسی
  • متن‌کاوی
  • تحلیل حساسیت
Alanyali, M., Moat, H. S., & Preis, T. (2013). Quantifying the relationship between financial news and the stock market. Scientific Reports, 3(1), 1-6. https://doi.org/10.1038/srep03578
 Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1–8. https://doi.org/10.1016/j.jocs.2010.12.007
Cavalcante, R. C., Brasileiro, R. C., Souza, V. L., Nobrega, J. P., & Oliveira, A. L. (2016). Computational intelligence and financial markets: A survey and future directions. Expert Systems with Applications55, 194-211.‏ https://doi.org/10. 1016/j.eswa.2016.02.006
Chan, S. W., & Chong, M. W. (2017). Sentiment analysis in financial texts. Decision Support Systems94, 53-64.‏ https://doi.org/10. 1016/j.dss. 2016.10.006
 Bachelier, L. L., & Cootner, P. H. (1964). The random character of stock market prices. Theorie de la speculation, Gauthiers, MIT Press. Cambridge.  
De Fortuny, E. J., De Smedt, T., Martens, D., & Daelemans, W. (2014). Evaluating and understanding text-based stock price prediction models. Information Processing & Management50(2), 426-441.‏ https://doi.org/10. 1016/j.ipm.2013.12.002
Dutta, A., Bandopadhyay, G., & Sengupta, S. (2012). Prediction of stock performance in the Indian stock market using logistic regression. International Journal of Business and Information, 7(1), 105-136.
Eck, M., Germani, J., Sharma, N., Seitz, J., & Ramdasi, P. P. (2020). Prediction of stock market performance based on financial news articles and their classification. In Sharma N., Chakrabarti A., Balas V.E., Martinovic J.   (Eds.), Data Management, Analytics and Innovation Advances in Intelligent Systems and Computing, vol 1175. (pp. 35-44). Springer. Singapore. https://doi.org/10.1007/978-981-15-5619-7_3
Fama, E. F. (1965). The behavior of stock-market prices. The journal of Business38(1), 34-105.‏ https://www.jstor.org/stable/2350752
Feuerriegel, S., & Gordon, J. (2018). Long-term stock index forecasting based on text mining of regulatory disclosures. Decision Support Systems, 112, 88-97. https://doi.org/10.1016/j.dss.2018.06.008
Forman, G. (2003). An extensive empirical study of feature selection metrics for text classification. Journal of Machine Learning Research, 3, 1289-1305.
Fung, G. P. C., Yu, J. X., & Lu, H. (2005). The Predicting power of textual information on financial markets. IEEE Intell. Informatics Bull, 5(1), 1-10.
Geva, T., & Zahavi, J. (2014). Empirical evaluation of an automated intraday stock recommendation system incorporating both market data and textual news. Decision support systems57, 212-223.
  Groth, S. S., & Muntermann, J. (2011). An intraday market risk management approach based on textual analysis. Decision Support Systems50(4), 680-691.‏ https://doi.org/10. 1016/j.dss.2010.08.019
Gunduz, H., & Cataltepe, Z. (2015). Borsa Istanbul (BIST) daily prediction using financial news and balanced feature selection. Expert Systems with Applications42(22), 9001-9011.‏ https://doi.org/10. 1016/j.eswa.2015.07.058
Guo, L., Shi, F., & Tu, J. (2016). Textual analysis and machine leaning: Crack unstructured data in finance and accounting. The Journal of Finance and Data Science2(3), 153-170.‏ https://doi.org/10. 1016/j.jfds.2017.02.001
Hagenau, M., Liebmann, M., & Neumann, D. (2013). Automated news reading: Stock price prediction based on financial news using context-capturing features. Decision Support Systems55(3), 685-697.‏ https://doi.org/10. 1016/j.dss.2013.02.006
Huang, J. Y., & Liu, J. H. (2020). Using social media mining technology to improve stock price forecast accuracy. Journal of Forecasting39(1), 104-116. https://doi.org/10.1002/for.2616
Hatefi Ghahfarrokhi, A., & Shamsfard, M. (2020). Tehran stock exchange prediction using sentiment analysis of online textual opinions. Intelligent Systems in Accounting, Finance and Management, 27(1), 22-37. https://doi.org/10.1002/isaf.1465
Hazm. (2019). https://pypi.org/project/hazm/. Retrieved January 29, 2019, from https://pypi.org/project/PyPrind/
Hong, S. (2020). A study on stock price prediction system based on text mining method using LSTM and stock market news. Journal of Digital Convergence, 18(7), 223-228. https://doi.org/10.14400/JDC.2020.18.7.223
Jishag, A. C., Athira, A. P., Shailaja, M., & Thara, S. (2020). Predicting the stock market behavior using historic data analysis and news sentiment analysis in R. In In: Luhach A., Kosa J., Poonia R., Gao XZ., Singh D.  (Eds.), First International Conference on Sustainable Technologies for Computational Intelligence. Advances in Intelligent Systems and Computing, vol 1045. (pp. 717-728). Springer, Singapore. https://doi.org/10.1007/978-981-15-0029-9_56
Kalra, V., & Agrawal, R. (2019). Challenges of text analytics in opinion mining. Extracting Knowledge from Opinion Mining (pp. 268-282). IGI Global.‏ https://doi.org/10.4018/978-1-5225-6117-0.ch012
Kavuluru, R., Hands, I., Durbin, E. B., & Witt, L. (2013). Automatic extraction of ICD-O-3 primary sites from cancer pathology reports. AMIA Summits on Translational Science Proceedings2013,  -116.‏
Kumar, B. S., & Ravi, V. (2016). A survey of the applications of text mining in financial domain. Knowledge-Based Systems114, 128-147.‏ https://doi.org/10. 1016/j.knosys.2016.10.003
Li, X., Xie, H., Chen, L., Wang, J., & Deng, X. (2014). News impact on stock price return via sentiment analysis. Knowledge-Based Systems69, 14-23.‏ https://doi.org/10. 1016/j.knosys. 2014.04.022
Li, Q., Wang, T., Li, P., Liu, L., Gong, Q., & Chen, Y. (2014). The effect of news and public mood on stock movements. Information Sciences278, 826-840.‏ https://doi.org/10. 1016/j.ins. 2014.03.096
Lutz, B., Pröllochs, N., & Neumann, D. (2020). Predicting sentence-level polarity labels of financial news using abnormal stock returns. Expert Systems with Applications, 148,  1-11. https://doi.org/10.1016/j.eswa.2020.113223
Mate, G. S., Kulkarni, R., Amidwar, S., & Muthya, (2020). Stock prediction through news sentiment analysis. Journal of Architecture & Technology, 11(8). 36-40.
Meesad, P., & Li, J. (2014, December). Stock trend prediction relying on text mining and sentiment analysis with tweets. In Choo, Y. H (Eds.), 4th World Congress on Information and Communication Technologies (WICT 2014) (pp. 257-262). IEEE. Melaka, Malaysia. https://doi.org/10.1109/WICT.2014.7077275
Moazeni, B., Nemati, M., & Sayyadi Moghaddam, M. (2014,  November). Investigating the impact of political and economic news on changes in the Tehran Stock Exchange Index. International Management Conference [Paper presentation]. Mobin Cultural Ambassadors Institute, Tehran, Iran   (In Persian).
Nassirtoussi, A. K., Aghabozorgi, S., Wah, T. Y., & Ngo, D. C. L. (2014). Text mining for market prediction: A systematic review. Expert Systems with Applications41(16), 7653-7670.‏ https://doi.org/10. 1016/j.eswa.2014.06.009
Narayan, P. K., & Bannigidadmath, D. (2017). Does financial news predict stock returns? New evidence from Islamic and non-Islamic stocks. Pacific-Basin Finance Journal, 42, 24-45. https://doi.org/10.1016/j.pacfin.2015.12.009
Nizer, P. S. M., & Nievola, J. C. (2012). Predicting published news effect in the Brazilian stock market. Expert Systems with Applications39(12),  .‏ https://doi.org/10. 1016/j.eswa.2012.02.162.
Nuij, W., Milea, V., Hogenboom, F., Frasincar, F., & Kaymak, U. (2013). An automated framework for incorporating news into stock trading strategies. IEEE Transactions on Knowledge and Data Engineering26(4), 823-835.‏ https://doi.org/10.1109/TKDE.2013.133.
Pejić Bach, M., Krstić, Ž., Seljan, S., & Turulja, L. (2019). Text mining for big data analysis in financial sector: A literature review. Sustainability, 11(5),  -1304. https://doi.org/10.3390/su11051277
Picasso, A., Merello, S., Ma, Y., Oneto, L., & Cambria, E. (2019). Technical analysis and sentiment embeddings for market trend prediction. Expert Systems with Applications, 135(201), 60-70. https://doi.org/10.1016/j.eswa.2019.06.014
Polyglot. (2019). Sentiment @ polyglot.readthedocs.io. Retrieved from https://polyglot.readthedocs.io/en/latest/Sentiment.html
Raschka, S., & Mirjalili, V. (2017). Machine learning mit Python und Scikit-Learn und TensorFlow: Das Praxis-Handbuch für Data Science, Predictive Analytics und Deep Learning. MITP Verlags GmbH & Company KG.
Rioja, F., & Valev, N. (2014). Stock markets, banks and the sources of economic growth in low and high income countries. Journal of Economics and Finance, 38(2), 302-320. https://doi.org/10.1007/s12197-011-9218-3
Ritesh, B. R., Chethan, R., & Jani, H. S. (2017). Stock movement prediction using machine learning on news articles. International Journal on Computer Science and Engineering, 4(3), 153-155.
Sharma, A., Bhuriya, D., & Singh, U. (2017, April). Survey of stock market prediction using machine learning approach. In Smys. S.   (Eds.) 2017 International conference of Electronics, Communication and Aerospace Technology (ICECA), 2, 506-509.‏ Coimbatore, India. https://doi.org/10.1109/ICECA.2017.8212715
Seker, S. E., Mert, C., Al-Naami, K., Ozalp, N., & Ayan, U. (2014). Time series analysis on stock market for text mining correlation of economy news. International Journal of Social Sciences and Humanity Studies6(1), 69-91.‏
Schumaker, R. P., & Chen, H. (2009). Textual analysis of stock market prediction using breaking financial news: The AZFin text system. ACM Transactions on Information Systems (TOIS), 27(2), 1-19. https://doi.org/10.1145/1462198.1462204
Schumaker, R. P., Zhang, Y., Huang, C. N., & Chen, H. (2012). Evaluating sentiment in financial news articles. Decision Support Systems53(3), 458-464.‏ https://doi.org/10. 1016/j.dss.2012.03.001.
Scrapy. (2019). index @ scrapy.org. Retrieved from https://scrapy.org/
Shynkevich, Y., McGinnity, T. M., Coleman, S. A., & Belatreche, A. (2016). Forecasting movements of health-care stock prices based on different categories of news articles using multiple kernel learning. Decision Support Systems, 85(2016), 74–83. https://doi.org/10.1016/j.dss.2016.03.001
Shynkevich, Y., McGinnity, T. M., Coleman, S., & Belatreche, A. (2015, July). Stock price prediction based on stock-specific and sub-industry-specific news articles. In Honorary, A. H  (Eds.), 2015 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE. Killarney, Ireland. https://doi.org/10.1109/IJCNN.2015.7280517
Tabari, N., Seyeditabari, A., Peddi, T., Hadzikadic, M., & Zadrozny, W. (2018, September). A comparison of neural network methods for accurate sentiment analysis of stock market tweets. In Alzate C. et al.   (Eds.), ECML PKDD 2018 Workshops. MIDAS 2018, PAP 2018. Lecture Notes in Computer Science, vol 11054. (pp. 51-65). Springer, Cham. https://doi.org/10.1007/978-3-030-13463-1_4.
Terra, J. (2021). Why Python is essential for data analysis and data science. Simplilearn. https://www.simplilearn.com/why-python-is-essential-for-data-analysis-article.
Thanh, H. T., & Meesad, P. (2014). Stock market trend prediction based on text mining of corporate web and time series data. Journal of Advanced Computational Intelligence and Intelligent Informatics, 18(1), 22-31. https://doi.org/10.20965/jaciii.2014.p0022
Tobback, E., Naudts, H., Daelemans, W., de Fortuny, E. J., & Martens, D. (2018). Belgian economic policy uncertainty index: Improvement through text mining. International Journal of Forecasting34(2), 355-365.‏ https://doi.org/10.1016/j.ijforecast.2016.08.006.
Tsai, C. F., Lin, Y. C., Yen, D. C., & Chen, Y. M. (2011). Predicting stock returns by classifier ensembles. Applied Soft Computing11(2), 2452-2459.‏ https://doi.org/10. 1016/j.asoc.2010.10.001.
Weng, B., Ahmed, M. A., & Megahed, F. M. (2017). Stock market one-day ahead movement prediction using disparate data sources. Expert Systems with Applications79, 153-163.‏ https://doi.org/10. 1016/j.eswa.2017.02.041.
W3Techs. (2019). https://w3techs.com/technologies/overview/content_language
Xie, Y., & Jiang, H. (2019). Stock market forecasting based on text mining technology: A support vector machine method. arXiv preprint arXiv:1909.12789.‏
Yekrangi, M., & Abdolvand, N. (2020). Financial markets sentiment analysis: Developing a specialized Lexicon. Journal of Intelligent Information Systems, 2020, 1-20. https://doi.org/10.1007/s10844-020-00630-9
Zaleskiewicz, T., & Traczyk, J. (2020). Emotions and financial decision making. In Zaleskiewicz T., Traczyk J.  (Eds.), Psychological Perspectives on Financial Decision Making (pp. 107-133). Springer, Cham. https://doi.org/10.1007/978-3-030-45500-2_6
Zhang, Z., Zhang, Y., Shen, D., & Zhang, W. (2018). The dynamic cross-correlations between mass media news, new media news, and stock returns. Complexity, special issue, 1-10, https://doi.org/10.1155/2018/7619494