STOCK SENTIMENT ANALYSIS FROM NEWS HEADLINES BY USING ENSEMBLE BOOSTING ALGORITHMS

Abstract

Stock sentiment analysis using machine learning techniques is an active area of research and development. Through these techniques, it is possible to analyze whether news headlines are likely to have a positive or negative sentiment, which is considered a potential factor influencing stock price movements. The analysis in this study is based on factors such as company-related news headlines and their publication dates. This study aims to introduce a stock sentiment analysis methodology based on Ensemble Boosting Algorithms. The dataset used consists of 3,897 unique news headlines from various companies. In addition to Ensemble Boosting Algorithms, widely used classification algorithms were also trained and compared. The results demonstrate that the proposed models achieved successful performance in sentiment classification.

Keywords

• Stock Sentiment Analysis
• Ensemble Learning
• Ensemble Boosting
• Ensemble Bagging

HABER BAŞLIKLARI KULLANILARAK HİSSE SENEDİ DUYGU ANALİZİ: TOPLULUK GÜÇLENDİRME ALGORİTMALARIYLA BİR YAKLAŞIM

Abstract

Hisse senedi duygu analizi, makine öğrenmesi teknikleri kullanılarak yürütülen aktif bir araştırma ve geliştirme alanıdır. Bu teknikler aracılığıyla, haber başlıklarının olumlu veya olumsuz bir duyguya sahip olma olasılığı analiz edilebilmekte ve bu durum, hisse senedi fiyat hareketlerini etkileyebilecek potansiyel bir faktör olarak değerlendirilmektedir. Bu çalışmada, şirketlerle ilgili haber başlıkları ve bu başlıkların yayın tarihleri dikkate alınarak bir duygu analizi yöntemi önerilmiştir. Çalışmada, Ensemble Boosting algoritmalarına dayalı bir hisse senedi duygu analizi metodolojisi geliştirilmiştir. Kullanılan veri seti, çeşitli şirketlere ait toplam 3.897 benzersiz haber başlığından oluşmaktadır. Ensemble Boosting algoritmalarına ek olarak, literatürde yaygın olarak kullanılan diğer sınıflandırma algoritmaları da eğitilmiş ve karşılaştırılmıştır. Elde edilen sonuçlar, önerilen modellerin haber başlıklarının duygu sınıflandırmasında başarılı performans sergilediğini göstermektedir.

Keywords

• Hisse Senedi Duygu Analizi
• Topluluk Öğrenme
• Topluluk Güçlendirme
• Topluluk Torbalama

References

1. Ali, S., & Yilmaz, A. (2021). Ensemble Learning for Enhanced Stock Sentiment Analysis Using Social Media and News Data. Journal of Financial Analytics, 17(3), 112–130.
2. Atan, S., & Cinar, Y. (2019). Examining The Relationship Between Financial News and Market Value in Borsa Istanbul Using Text Mining and Sentiment Analysis. (Borsa Istanbul’da Finansal Haberler ile Piyasa Degeri İliskisinin Metin Madenciligi ve Duygu (Sentiment) Analizi ile İncelenmesi). Ankara University, The Faculty of Political Sciences Journal, 74 (1), pp. 1-34.
3. Bacanin, N., Zivkovic, M., Stoean, C., Antonijevic, M., Janicijevic, S., Sarac, M., & Strumberger, I. (2022). Application of Natural Language Processing and Machine Learning Boosted with Swarm Intelligence for Spam E-mail Filtering. Mathematics, 10 (22), pp. 4173. https://doi.org/10.3390/math10224173
4. Bentéjac, C., Csörgő, A., & Martínez-Muñoz, G. (2021). A comparative Analysis of Gradient Boosting Algorithms. Artificial Intelligence Review, 54, pp. 1937-1967. https://doi.org/10.1007/s10462-020-09896-5
5. Bollen, J., Mao, H., & Zeng, X. (2011). Twitter Mood Predicts the Stock Market. Journal of Computational Science, 2 (1), pp. 1-8. https://doi.org/10.1016/j.jocs.2010.12.007
6. Brown, T., & Nguyen, P. (2022). Portfolio Optimization Using Ensemble Learning Approaches. International Journal of Investment Science, 9(3), 230–245.
7. Chen, S., Webb, G. I., Liu, L., & Ma, X. (2020). A novel selective naïve Bayes algorithm. Knowledge-Based Systems, 192, 105361. https://doi.org/10.1016/j.knosys.2019.105361
8. Demajo, Lara. (2020). Explainable AI For Interpretable Credit Scoring. Thesis M.Sc. University of Malta.

9. Demir, B., & Koc, E. (2022). Comparative Evaluation of Ensemble Methods in Stock Sentiment Analysis During Market Uncertainty. Journal of Computational Finance, 20(1), 45–63.
10. Demir, F., & Can, G. (2023). Comparative Analysis of Ensemble Methods in Machine Learning. Journal of Data Science, 12(2), 89–105.
11. Fu, H., & Qi, K. (2022). Evaluation Model of Teachers' Teaching Ability Based on Improved Random Forest with Grey Relation Projection. Scientific Programming, pp. 1-12. http://dx.doi.org/10.1155/2022/5793459
12. Garcia, M., Patel, S., & Kim, H. (2023). Ensemble Methods For Credit Scoring: A Modern Perspective. Journal of Banking Analytics, 8(1), 50–68.
13. Hasan, M., & Islam, S. (2020). Stock Market Sentiment Analysis Using Financial News Articles. International Journal of Business and Data Analytics, 2 (3), pp. 112-126.
14. Hu, J., & Szymczak, S. (2023). A Review on Longitudinal Data Analysis with Random Forest. Briefings in Bioinformatics, 24 (2). https://doi.org/10.1093/bib/bbad002
15. Janiesch, C., Zschech, P., & Heinrich, K. (2021). Machine Learning and Deep Learning. Electronic Markets, 31 (3), pp.685-695. https://doi.org/10.1007/s12525-021-00475-2
16. Javapoint, GBM in Machine Learning from https://www.javatpoint.com/gbm-in-machine-learning (Access date: 20 January 2024).
17. Kaggle.com, from https://www.kaggle.com/code/siddharthtyagi/stock-sentiment-analysis-using-news-headlines/input (Access date: 15/10/2023).
18. Kara, C., Demir, E., & Yilmaz, S. (2022). Boosting Techniques: An Overview Of Recent Advancements. International Journal of Artificial Intelligence, 29(1), 45–62.
19. Lestari, N., Riza, O. S., & Ardinal, R. (2023). Implementation of Text Mining and Pattern Discovery with Naive Bayes Algorithm for Classification of Text Documents. Digital Zone: Jurnal Teknologi Informasi dan Komunikasi, 14 (1), pp. 88-102. https://doi.org/10.31849/digitalzone.v14i1.13596
20. Li, X., & Zhang, Y. (2021). Ensemble Learning in Financial Risk Management. Journal of Financial Data Science, 4(2), 100–115.
21. Osman, A. I. A., Ahmed, A. N., Chow, M. F., Huang, Y. F., & El-Shafie, A. (2021). Extreme Gradient Boosting (XGboost) Model to Predict the Groundwater Levels in Selangor Malaysia. Ain Shams Engineering Journal, 12 (2), pp. 1545-1556. https://doi.org/10.1016/j.asej.2020.11.011
22. Ozdemir, A., & Yilmaz, B. (2021). Ensemble Learning and Its Applications in Predictive Modeling. Journal of Advanced Machine Learning, 15(3), 210–225.
23. Rincy, T. N., & Gupta, R. (2020). Ensemble Learning Techniques and Its Efficiency in Machine Learning: A Survey. In 2nd international conference on data, engineering and applications (IDEA) February, (pp. 1-6). IEEE. https://doi.org/10.1109/IDEA49133.2020.9170675
24. Sarker, I. H. (2021). Machine learning: Algorithms, Real-World Applications and Research Directions. SN computer science, 2 (3), pp. 160. https://doi.org/10.1007/s42979-021-00592-x
25. Shyrokykh, K., Girnyk, M., & Dellmuth, L. (2023). Short Text Classification with Machine Learning in The Social Sciences: The Case of Climate Change on Twitter. Plos one, 18 (9), e0290762. https://doi.org/10.1371/journal.pone.0290762
26. Ustali, N. K., Tosun, N., & Tosun, O. (2021). Stock Price Prediction with Machine Learning Techniques (Makine Ögrenmesi Teknikleri ile Hisse Senedi Fiyat Tahmini). Eskişehir Osmangazi University, Journal of Economic and Administrative Sciences, 16 (1), pp. 1-16. https://doi.org/10.17153/oguiibf.636017
27. Wang, H., Li, J., & Chen, M. (2023). Minimizing Semantic Loss in Deep Ensemble Models for Stock Sentiment Prediction. International Journal of Data Science and Financial Analytics, 11(2), 89–107.
28. Wang, S. and Yang, Y. (2021), "M-GAN-XGBOOST Model for Sales Prediction and Precision Marketing Strategy Making of Each Product in Online Stores". Data Technologies and Applications, 55(5), pp. 749-770. https://doi.org/10.1108/DTA-11-2020-0286
29. Wang, Y., & Guo, Y. (2020). Forecasting Method of Stock Market Volatility in Time Series Data Based on Mixed Model of ARIMA and XGBoost. China Communications, 17 (3), pp. 205-221. https://doi.org/10.23919/JCC.2020.03.017
30. Yewale, D., Vijayaragavan, S. P., & Munot, M. (2023, June). An Optimized XGBoost Based Classification Model for Effective Analysis of Heart Disease Prediction. In AIP Conference Proceedings (Vol. 2768, No. 1). AIP Publishing. https://doi.org/10.1063/5.0148268
31. Yigiter, S. Y., Sari, S. S., & Basakin, E. E. (2017). Predicting stock Closing Prices with Artificial Neural Networks and Fuzzy Logic Inference Systems (Hisse Senedi Kapanış Fiyatlarının Yapay Sinir Ağları ve Bulanık Mantık Çıkarım Sistemleri ile Tahmin Edilmesi).
32. Yildirim, M., & Yuksel, C. A. (2017). Examining The Relationship Between Social Media and Daily Stock Price Movement Direction: Application of Sentiment Analysis (Sosyal Medya İle Hisse Senedi Fiyatının Günlük Hareket Yönü Arasındaki İlişkinin İncelenmesi: Duygu Analizi Uygulaması). International Journal of Economic and Administrative Studies, pp. 33-44.