Relationship Between Twitter Sentiment Analysis and Bitcoin Prices: Econometric Analysis of Long and Short Term Dynamics

Year 2024, Volume: 9 Issue: 2, 605 - 626, 30.06.2024

Çağrı Ulu , Cansu Ulu

https://doi.org/10.25229/beta.1432142

Abstract

The significance of social media in influencing cryptocurrency pricing has grown considerably in recent years. This study aims to explore the correlations between social media sentiments and Bitcoin pricing, both in the short and long terms, while also investigating the direction of these relationships. Sentiment analysis was conducted using the TextBlob model, which uncovers the underlying meaning in text through analysis. The study tested the hypothesis that there exists a relationship between sentiment analysis scores and Bitcoin prices over both short and long periods. Ensuring stationarity was crucial for time series analysis, involving the use of structural break and traditional unit root tests. Daily data from June 2021 to June 2022 was examined, with December 2021 serving as the focal point due to a peak in Bitcoin prices. The study focused on Bitcoin price data and sentiment analysis scores. Results revealed Twitter data as the dependent variable, showing no long-term relationship with Bitcoin prices. However, a significant and positive relationship was observed in the short term. This research contributes valuable insights into the intricate dynamics between social media sentiments and cryptocurrency pricing.

Keywords

Bitcoin, Twitter, Sentiment Analysis, ARDL Bounds Test, Text mining

Twitter Duyarlılık Analizi ile Bitcoin Fiyatları Arasındaki İlişki: Uzun ve Kısa Dönem Dinamiklerin Ekonometrik Analizi

Abstract

Sosyal medyanın kripto para birimi fiyatlandırmasını etkilemedeki önemi son yıllarda önemli ölçüde artmıştır. Bu çalışma, sosyal medya duyarlılığı ile Bitcoin fiyatlandırması arasındaki ilişkileri hem kısa hem de uzun vadede araştırmaktadır. Aynı zamanda bu ilişkilerin yönünü tespit etmeyi amaçlamaktadır. Duyarlılık analizi, metnin altında yatan anlamı ortaya çıkaran TextBlob modeli kullanılarak gerçekleştirilmiştir. Çalışma, duyarlılık analizi puanları ile Bitcoin fiyatları arasında hem kısa hem de uzun vadede bir ilişki olduğu hipotezini test etmiştir. Durağanlığın sağlanması, yapısal kırılma ve geleneksel birim kök testlerinin kullanımını içeren zaman serisi analizine imkan sağlamıştır. Çalışma kapsamındaHaziran 2021'den Haziran 2022'ye kadar olan günlük veriler incelenmiştir ve Bitcoin fiyatlarındaki zirve nedeniyle Aralık 2021 odak noktası kabul edilmiştir. Çalışma Bitcoin fiyat verilerine ve duyarlılık analizi puanlarına odaklanmaktadır. Sonuçlar, Bitcoin fiyatlarıyla uzun vadeli bir ilişki göstermeyen Twitter verilerinin bağımlı değişken olduğunu ortaya çıkarmıştır. Ancak kısa vadede anlamlı ve pozitif bir ilişki gözlenmiştir. Bu araştırma, sosyal medya duyarlılığı ile kripto para birimi fiyatlandırması arasındaki karmaşık dinamiklere dair literatüre değerli bilgiler sağlamaktadır.

Keywords

Bitcoin, Twitter, Sentiment Analysis, ARDL Bounds Test, Text mining

References

• Baykal, A. (2006). Veri madenciliği uygulama alanları. D.Ü. Ziya Gökalp Eğitim Fakültesi Dergisi, (7), 95-107.
• Brown, R. L., Durbin, J., & Evans, J. M. (1975). Techniques for testing the constancy of regression relationships over time. Royal Statistical Society, 37(2), 149-192.
• Chalkiadakis, I. G., Peters, W., & Ames, M. (2021). Hybrid ARDL-MIDAS-transformer time-series regressions for multi-topic crypto market sentiment driven by price and technology factors. SSRN. https://papers.ssrn.com/sol3/ papers.cfm?abstract_id=3908066 (Accessed on: 18.04.2022).
• Chen, N. (2022). Bitcoin price and miner behavior: An application of ARDL model. Journal of Financial Studies & Research, 2022, 1-16.
• Dickey, D. A., & Fuller, W. A. (1979). Distribution of the estimators for autoregressive time series with a unit root. Journal of the American Statistical Association, 74(366), 427-431.
• Enders, W., & Lee, J. (2012). The flexible Fourier form and Dickey–Fuller type unit root tests. Economics Letters, 117(1), 196-199.
• Engle, R. F., & Granger, C. W. (1987). Cointegration and error correction: Representation, estimation and testing. Econometrica, 55(2), 251-276.
• Gaies, B., Nakhli, M. S., Sahut, J. M., & Guesmi, K. (2021). Is Bitcoin rooted in confidence? – Unraveling the determinants of globalized digital currencies. Technological Forecasting & Social Change, 172, 1-11.
• Galeshchuk, S., Vasylchyshyn, O., & Krysovatyy, A. (2018). Bitcoin response to Twitter sentiments. ICTERI Workshops, Kiev, Ukraine, pp.160-168.
• Gözbaşi, O., Altinöz, B., & Şahin, E. E. (2021). Is Bitcoin a safe haven? A study on the factors that affect Bitcoin prices. International Journal of Economics and Financial Issues, Econjournals, 11(4), 35-40.
• Kahneman, D., & Tversky, A. (1979). Prospect theory: An analysis of decision under risk. Econometrica, 47(2), 263-292.
• Katsafados, A. G., Nikoloutsopoulos, S., & Leledakis, G. N. (2023). Twitter sentiment and stock market: A COVID-19 analysis. Journal of Economic Studies. https://doi.org/10.1108/JES-09-2022-0486.
• Kjærland, F., Meland, M., Oust, A., & Øyen, V. (2018). How can Bitcoin price fluctuations be explained?. International Journal of Economics and Financial Issues, 8(3), 323-332.
• Li, X., & Wang, C. A. (2021). The technology and economic determinants of cryptocurrency exchange rates: The case of Bitcoin. Decision Support Systems, 95, 49-60.
• Newey, W. K., & West, K. D. (1987). A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix. Econometrica, 55(3), 703–708.
• NLTK. (2023). Documentation. https://www.nltk.org/ (Accessed on: 19.04.2023).
• Pesaran, M. H., Shin, Y., & Smith, R. J. (2001). Bounds testing approaches to the analysis of level relationships. Journal of Applied Econometrics, 16(3), 289-326.
• Phillips, C. B. P., & Perron, P. (1988). Testing for a unit root in time series regression. Biometrika, 75(2), 335-346.
• Polat, A. Y. (2021). Davranışsal finans teorisi ve kripto paralar. Efe Akademi.
• Rajput, S. K. O., Soomro, I. A., & Soomro, N. A. (2022). Bitcoin sentiment index, Bitcoin performance and US dollar exchange rate. Journal of Behavioral Finance, 23(2), 150-165.
• Sattarov, O., Jeon, H. S., Oh, R., & Lee, J. D. (2020). Forecasting Bitcoin price fluctuation by Twitter sentiment analysis. 2020 International Conference on Information Science and Communications Technologies (ICISCT), Taşkent, Özbekistan, 1-4.
• Shahvari, N. (2022). The relation between gold price movement and Bitcoin investment sentiment. International Journal of Management, Accounting and Economics, 9(9), 566-582.
• Wong, E. L. X. (2021). Prediction of Bitcoin prices using Twitter data and natural language processing. Duke University Libraries Duke Space. https://dukespace.lib.duke.edu/dspace/handle/10161/24081 (Accessed on: 18.04.2023).