Twitter ile Hisse Senetleri Oynaklığı Tahmin Edilebilir mi?

Year 2020, Volume: 28 Issue: 45, 315 - 326, 30.07.2020

Gürkan Bozma , Sinan Kul

https://doi.org/10.17233/sosyoekonomi.2020.03.18

Cited By: 2

Abstract

Tweetlerin duygu analizi ile hisse senedi fiyat hareketleri arasında ilişki olduğu hatta hisse senedi fiyatlarının bu yolla tahmin edilebildiği yapılan çalışmalarla ortaya konmuştur. Tweetlerin, hisse senetlerinin oynaklığına etkisinin tahmin edilmesi üzerine yapılan bu çalışmada ayrıca, hisse senetlerinin birbirleri arasındaki ve duygu puanlarının hisse senetleri arasındaki oynaklık geçişkenlikleri de ortaya çıkarılmıştır. Çalışma kapsamında, ürünlerinin Türkiye’de satışı yapılan ve Borsa İstanbul’da faaliyet gösteren 3 telefon markası (Alcatel, Turkcell ve Vestel) hakkında paylaşılan Türkçe tweetler üzerinde Naive Bayes ile duygu analizi yapılmıştır. Analiz sonuçlarına göre Turkcell ve Vestel için elde edilen duygu puanlarının Arcatel’in koşullu varyansını istatistiki olarak anlamlı bir şekilde artırdığı tespit edilmiştir.

Keywords

Duygu Analizi, Türkçe Tweet, Doğal Dil İşleme, Veri Madenciliği, Metin Madenciliği, Borsa Tahmini, Makine Öğrenmesi, Naive Bayes, BEKK-GARCH-X

Can Twitter Forecast Uncertainty of Stocks?

Abstract

Academic studies have shown that there is a relationship between emotional analysis results of tweets and stock price movements, and then stock prices can be estimated using this relationship. In this study, in which the effect of tweets on the volatility of the stock is estimated, the volatility scores and the emotion scores between the stocks were also revealed. In the scope of the study, sentiment analysis with Naive Bayes was performed on Turkish tweets shared by three phone companies (Alcatel, Turkcell and Vestel) which are in Borsa Istanbul and whose products are sold in Turkey. According to the results of the analysis, it was found that sentiment scores obtained for Turkcell and Vestel significantly increased Alcatel's conditional variance statistically.

Keywords

Naive Bayes, Sentiment Analysis, Turkish Tweet, Natural Language Processing, Data Mining, Text Mining, Stock Market Prediction, Machine Learning, BEKK-GARCH-X

References

• Aich, S., Kim, H. C., Sain, M., & Deo, B. B. (2017, February). Analyzing stock price changes using event related Twitter feeds. In 2017 19th International Conference on Advanced Communication Technology (ICACT) (pp. 484-487). IEEE.
• Akarsu, C., & Diri, B. (2016). "Twitter ile Türk Televizyonları Rating Tahmini" [Bildiri]. The Signal Processing and Communication Application Conference (SIU), 2016 24th, Zonguldak.
• Attigeri, G. V., MM, M. P., Pai, R. M., & Nayak, A. (2015, November). Stock market prediction: A big data approach. In TENCON 2015-2015 IEEE Region 10 Conference (pp. 1-5). IEEE.
• Bian, J., Topaloglu, U., & Yu, F. (2012). "Towards large-scale twitter mining for drugrelated adverse events" [Bildiri]. The Proceedings of the 2012 international workshop on Smart health and wellbeing
• Bing, L., Chan, K. C., & Ou, C. (2014, November). Public sentiment analysis in Twitter data for prediction of a company's stock price movements. In 2014 IEEE 11th International Conference on e-Business Engineering (pp. 232-239). IEEE.
• Bollen, J., Mao, H., & Zeng, X. (2011). "Twitter Mood Predicts the Stock Market" [Twitter Ruh Hali Borsayı Tahmin Eder]. Journal of Computational Science, 2(1), 1-8.Cakra, Y. E., & Trisedya, B. D. (2015, October). Stock price prediction using linear regression based on sentiment analysis. In 2015 International Conference on Advanced Computer Science and Information Systems (ICACSIS) (pp. 147-154). IEEE.
• Claster, W. B., Dinh, H., & Cooper, M. (2010). "Naive Bayes and Unsupervised Artificial Neural Nets for Cancun Tourism Social Media Data Analysis" [Bildiri]. The Nature and Biologically Inspired Computing (NaBIC), 2010 Second World Congress on, Kitakyushu, Japan.
• Çoban, Ö., Özyer, B., & Özyer, G. T. (2015, May). Sentiment analysis for Turkish Twitter feeds. In 2015 23nd Signal Processing and Communications Applications Conference (SIU) (pp. 2388-2391). IEEE.
• Engle, R. & Kroner, K. 1995. Multivariate simultaneous generalized ARCH. Econometric Theory 11: 122–150.
• Hu, Z., Jiao, J., & Zhu, J. (2014). Using Tweets to Predict the Stock Market.
• Nguyen, L. T., Wu, P., Chan, W., Peng, W., & Zhang, Y. (2012). "Predicting Collective Sentiment Dynamics From Time-Series Social Media" [Bildiri]. The Proceedings of the first international workshop on issues of sentiment discovery and opinion mining, Çin.
• Nofer, M., & Hinz, O. (2015). Using twitter to predict the stock market. Business & Information Systems Engineering, 57(4), 229-242.
• Pagolu V. S., Challa, K. N. R., Panda G. & Majhi B. (2016). “Sentiment Analysis of Twitter Data for Predicting Stock Market Movements” [Bildiri]. International conference on Signal Processing, Communication, Power and Embedded System (SCOPES)-2016
• Qasem, M., Thulasiram, R., & Thulasiram, P. (2015, August). Twitter sentiment classification using machine learning techniques for stock markets. In 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 834-840). IEEE.
• Si, J., Mukherjee, A., Liu, B., Pan, S. J., Li, Q., & Li, H. (2014, October). Exploiting social relations and sentiment for stock prediction. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1139-1145).
• Skuza, M., & Romanowski, A. (2015, September). Sentiment analysis of Twitter data within big data distributed environment for stock prediction. In 2015 Federated Conference on Computer Science and Information Systems (FedCSIS) (pp. 1349-1354). IEEE.
• Szomszor, M., Kostkova, P., & De Quincey, E. (2010). "Swineflu: Twitter Predicts Swine Flu Outbreak in 2009". International Conference on Electronic Healthcare, 69, 18-26.
• Şimşek, M. U., & Özdemir, S. (2012). "Analysis of the Relation Between Turkish Twitter Messages and Stock Market Index" [Bildiri]. The 6th International Conference: Application of Information and Communication Technologies (AICT), Tbilisi, Georgia.
• Türkmenoglu, C., & Tantug, A. C. (2014). "Sentiment Analysis in Turkish Media" [Bildiri]. The International Conference on Machine Learning, Çin.
• Wei, W., Mao, Y., & Wang, B. (2016). Twitter volume spikes and stock options pricing. Computer Communications, 73, 271-281.