Sosyal Medya ve Diğer Yatırım Aracı Verilerine Dayalı Hisse Senedi Değeri Tahmini

Year 2021, Volume: 5 Issue: 2, 267 - 285, 30.12.2021

Ömer Faruk Uyrun , İbrahim Sabuncu

Abstract

Bu çalışmada, farklı makine öğrenmesi teknikleriyle yatırım aracı verileri ile birlikte sosyal medya verileri kullanılarak hisse senedi tahminlenmesi amaçlanmıştır. Çalışma kapsamında, beş farklı havayolu firmasına ilişkin Ekim 2019 – Şubat 2020 dönemine ait 236 764 adet tweet ve söz konusu şirketlerin hisse senedi değeri ve işlem gördüğü borsanın günlük verileri, dolar kuru ve altın fiyatları ele alınmış olup, tweet’lerin analizinde duygu analizi gerçekleştirilmiştir. Çalışmada, Gradyan Destekli Ağaçlar (Gradient Boosted Trees) algoritmasının hisse senedi tahminlemesinde en düşük hata payına sahip tahmin modeli olduğu tespit edilmiş olup, şirketler hakkındaki net pozitif (pozitif-negatif) tweet sayılarının hisse senedi değeri tahminindeki en etkili faktörlerden birisi olduğu görülmüştür. Çalışma sonucunda, Gradyan Destekli Ağaçlar algoritmasının çalışma kapsamında kullanılan diğer algoritmalara göre hisse senedi tahminlemesinde etkin olduğu ve Twitter verisinin diğer yatırım verileri ile birlikte hisse senedi değeri tahmininde faydalanılabilecek bir veri kaynağı olduğu düşünülmektedir.

Keywords

Sosyal Medya Analitiği, Veri Madenciliği, Tahmin Modeli, Hisse Değeri, Twitter

Supporting Institution

Yalova Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimi

Project Number

2019/YL/0001

Forecasting Stock Value Based on Data from Social Media and Investment Instruments

Abstract

This study aimed to predict stocks using different machine learning techniques with social media data and investment instrument data. Within the scope of the study, 236,764 tweets related to five different airline companies during the period October 2019 - February 2020, the stock value of those companies, the daily data of the stock market, dollar rate and gold prices were discussed. Additionally, sentiment analysis was carried out in the analysis of the tweets. In the study, it was determined that the Gradient Boosted Trees algorithm was the prediction model with the lowest margin of error in stock prediction, and it was seen that the number of net positives (positive-negative) tweets about companies was one of the most influential factors in forecasting stock value. As a result of the study, it is thought that the Gradient Boosted Trees algorithm is effective in stock prediction compared to the other algorithms used in the study, and that Twitter data is a data source that can be used in forecasting stock value together with other investment data.

Keywords

Social Media Analytics, Data Mining, Prediction Model, Stock Value, Twitter

Project Number

2019/YL/0001

References

• Aktaş, M., & Akdağ, S. (2013). Türkiye’de Ekonomi̇k Faktörleri̇n Hi̇sse Senedi̇ Fi̇yatları İle İli̇şki̇leri̇ni̇n Araştırılması. International Journal of Social Science Research (Las Vegas, Nev.), 2(1), 50–67.
• Arun, K., Srinagesh, A., & Ramesh, M. (2017). Twitter Sentiment Analysis on Demonetization tweets in India Using R language. International Journal of Computer Engineering In Research Trends, 4(6), 252–258. Tarihinde adresinden erişildi www.ijcert.org
• Asur, S., & Huberman, B. A. (2010). Predicting the future with social media. Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010, 1(March 2010), 492–499. https://doi.org/10.1109/WI-IAT.2010.63
• Attigeri, G. V, M, M. P. M., Pai, R. M., & Nayak, A. (2015). Stock market prediction: A big data approach. TENCON 2015 - 2015 IEEE Region 10 Conference, 1–5. https://doi.org/10.1109/TENCON.2015.7373006
• Bhardwaj, A., Narayan, Y., & Dutta, M. (2015). Sentiment Analysis for Indian Stock Market Prediction Using Sensex and Nifty. 70, 85–91. https://doi. org/10.1016/j.procs.2015.10.043
• 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
• Charan, A. (2015). Marketing analytics: A Practitioner’s Guide to Marketing Analytics and Research Methods. World Scientific Publishing Company.
• Chen, R., & Lazer, M. (2011). Sentiment Analysis of Twitter Feeds for the Prediction of Stock Market Movement. 1–5.
• Cingöz, F., & Kendirli, S. (2019). Altın Fi̇yatları, Dövi̇z Kuru ve Borsa İstanbul Arasindak İli̇şki̇. Finans Ekonomi ve Sosyal Araştırmalar Dergisi, 545–554. https://doi.org/10.29106/fesa.649254
• Das, S., & Behera, R. K. (2018). Real-Time Sentiment Analysis of Twitter Streaming data for Stock Prediction. Procedia Computer Science, 132(Iccids), 956–964. https://doi.org/10.1016/j.procs.2018.05.111
• Das, S. R., Kim, S., & Kothari, B. (2017). Zero-Revelation RegTech: Detecting Risk through Linguistic Analysis of Corporate Emails and News. SSRN Electronic Journal, 0–32. https://doi.org/10.2139/ssrn.2909380
• Dickinson, B., & Hu, W. (2015). Sentiment Analysis of Investor Opinions on Twitter. Social Networking, 04(03), 62–71. https://doi.org/10.4236/sn.2015.43008
• Dolapcı, B. (2020). APACHE SPARK KULLANILARAK BÜYÜK BOYUTLU GÖRÜNTÜLERİN ANALİZİ. Karabük Üniversitesi.
• Eliaçik, A. B., & Erdogan, N. (2015). Mikro Bloglardaki Finans Toplulukları için Kullanıcı Ağırlıklandırılmış Duygu Analizi Yöntemi. Ulusal Yazılım Mühendisliği Sempozyumu, 782–793.
• Evans, J. R. (2016). Business Analytics (2nd baskı). Boston: Pearson Education.
• Gazioğlu, K., & Şeker, Ş. E. (2017). Veri Madenciliği Yöntemleri ile Twitter Üzerinden Girişimcilik Analizi. 3–10.
• Gençtürk, M. (2009). Finansal Kriz Dönemlerinde Makroekonomik Faktörlerin Hisse Senedi Fiyatlarına Etkisi. Süleyman Demirel Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 14/1, 127–136.
• Holsapple, C. W., Hsiao, S.-H., & Pakath, R. (2018). Business social media analytics: Characterization and conceptual framework. Decision Support Systems. https://doi.org/https://doi.org/10.1016/j.dss.2018.03.004
• investing. (2020a). Altın-Try. Tarihinde 03 Ocak 2020, adresinden erişildi https://tr.investing.com/currencies/gau-try
• investing. (2020b). BİST-100 hisse değeri. Tarihinde 01 Mart 2020, adresinden erişildi https://tr.investing.com/indices/ise-100
• investing. (2020c). “investing.com” internet sitesi. Tarihinde 06 Şubat 2020, adresinden erişildi https://tr.investing.com/
• investing. (2020d). SIAL hisse değeri. Tarihinde 06 Şubat 2020, adresinden erişildi https://tr.investing.com/equities/singapore-airlines
• investing. (2020e). Singapore Exchange(SGXL/SGD). Tarihinde 06 Şubat 2020, adresinden erişildi https://tr.investing.com/equities/ singapore-exchange
• investing. (2020f). Usd-Try. Tarihinde 01 Mart 2020, adresinden erişildi https://tr.investing.com/currencies/usd-try-chart
• investing. (2020g). USD/SGD değeri. Tarihinde 06 Şubat 2020, adresinden erişildi https://tr.investing.com/currencies/usd-sgd
• Karahan, M. (2011). İstatistiksel Tahmin Yöntemleri: Yapay Sinir Ağları Metodu ile Ürün Talep Tahmini Uygulaması. Selçuk Üni̇versi̇tesi̇ Sosyal Bi̇li̇mler Ensti̇tüsü İşletme Anabi̇li̇m Dalı, 112–113.
• Lee, I. (2018). Social media analytics for enterprises: Typology, methods, and processes. Business Horizons, 61(2), 199–210. https://doi.org/https://doi. org/10.1016/j.bushor.2017.11.002
• Mittal, A., & Goel, A. (2012). Stock Prediction Using Twitter Sentiment Analysis. http://cs229.stanford.edu/proj2011/GoelMittal-StockMarketPredictio nUsingTwitterSentimentAnalysis.pdf, (December). Tarihinde adresinden erişildi http://cs229.stanford.edu/proj2011/GoelMittal-StockMarketPredict ionUsingTwitterSentimentAnalysis.pdf
• Murugesan, S. (2007). Understanding Web 2.0. IT Professional, 9(4), 34–41. https://doi.org/10.1109/MITP.2007.78
• Özüpek, M. N., & Diker, E. (2013). İLETİŞİM FAKÜLTESİ ÖĞRENCİLERİNİN CEP TELEFONU MARKALARINA YÖNELİK İMAJ ALGISI: NOKIA VE SAMSUNG ÖRNEĞİ ÖZET. New World Sciences Academy, 369(1), 100–120. Tarihinde adresinden erişildi http://dx.doi.org/10.1016/j. jsames.2011.03.003%0Ahttps://doi.org/10.1016/j.gr.2017.08.001%0Ahttp://dx.doi.org/10.1016/j.precamres.2014.12.018%0Ahttp://dx.doi.org/10.1016/j. precamres.2011.08.005%0Ahttp://dx.doi.org/10.1080/00206814.2014.902757%0Ahttp://dx.
• Pagolu, V. S., & Majhi, B. (2016). Sentiment Analysis of Twitter Data for Predicting Stock Market Movements. 2016 International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), 1345–1350. https://doi.org/10.1109/SCOPES.2016.7955659
• Porshnev, A., Redkin, I., & Shevchenko, A. (2013). Machine learning in prediction of stock market indicators based on historical data and data from Twitter sentiment analysis . 2013 IEEE 13th International Conference on Data Mining Workshops, 440–444. https://doi.org/10.1109/ICDMW.2013.111
• Rapid Miner. (2019). Gradient Boosted Trees Model. Tarihinde 06 Şubat 2020, adresinden erişildi https://docs.rapidminer.com/latest/studio/operators/ modeling/predictive/trees/gradient_boosted_trees.html
• Salo, J. (2017). Social media research in the industrial marketing field: Review of literature and future research directions. Industrial Marketing Management, 66, 115–129. https://doi.org/https://doi.org/10.1016/j.indmarman.2017.07.013
• Si, J., Mukherjee, A., Liu, B., & Li, Q. (2013). Exploiting Topic based Twitter Sentiment for Stock Prediction. (2011), 24–29.
• Skytrax. (2020). 2019 World Airline Ranking List. Tarihinde 10 Şubat 2020, adresinden erişildi https://www.worldairlineawards.com/ worlds-top-100-airlines-2019/
• Syam, N., & Sharma, A. (2018). Waiting for a sales renaissance in the fourth industrial revolution: Machine learning and artificial intelligence in sales research and practice. Industrial Marketing Management, 69, 135–146. https://doi.org/https://doi.org/10.1016/j.indmarman.2017.12.019
• Tripathi, P., Vishwakarma, S. K., & Lala, A. (2015). Sentiment Analysis of English Tweets Using Rapid Miner. 2015 International Conference on Computational Intelligence and Communication Networks (CICN).
• Ulusoy, N. (2012). Sözlüklerdeki Sinema Sevgisi: New York’ta Beş Minare ve Çoğunluğun İnternet Sözlüklerine Yansıması. Beta Yayıncılık, 195–211.
• Vu, T. T., Chang, S., Quang, T. H., & Collier, N. (2012). An Experiment in Integrating Sentiment Features for Tech Stock Prediction in Twitter. Proceedings of the Workshop on Information Extraction and Entity Analytics on Social Media Data, 3, 23–38.
• Yadav, R., Kumar, A. V., & Kumar, A. (2019). News-based supervised sentiment analysis for prediction of futures buying behaviour. IIMB Management Review, 31(2), 157–166. https://doi.org/10.1016/j.iimb.2019.03.006
• Yıldırım, M., & Yüksel, C. A. (2017). Sosyal Medya İle Hi̇sse Senedi̇ Fi̇yatinin Günlük Hareket Yönü Arasinda İli̇şki̇ni̇ İncelenmesi̇: Duygu Anali̇zi̇ Uygulamasi. Uluslararası İktisadi ve İdari İncelemeler Dergisi. https://doi.org/10.18092/ulikidince.352414
• Zhang, X., Fuehres, H., & Gloor, P. A. (2011). Predicting Stock Market Indicators Through Twitter “ I hope it is not as bad as I fear ”. Procedia - Social and Behavioral Sciences, 26(2007), 55–62. https://doi.org/10.1016/j.sbspro.2011.10.562