Abstract
Forecasting various economic indicators has been a primary interest in economics and has attracted the attention of many researchers. Granger causality analysis has become quite popular in the econometrics literature and it aims to determine whether one time series is useful in forecasting another. In this work through the use of Granger causality analysis we investigate whether Twitter sentiment, expressed in large scale collections of daily tweets, can be correlated or even predictive of future prices of cryptocurrencies. The proposed framework considers tweets that mention the cryptocurrency “Dogecoin” and analyses the textual content of each of these tweets using a modified version of the lexicon-based sentiment polarity analysis method, VADER. The generated, Twitter sentiment time series is then compared to a time series of the closing prices of Dogecoin for each day. Granger causality analysis showed a unidirectional relationship between Twitter sentiment and cryptocurrency prices for day lags ranging from 2 to 4 days (with a 3-day lag having the lowest statistical significance value). This was also accompanied by a Pearson correlation coefficient of \(r = 0.6940\) and a clear visual correlation between the two time series (with this 3-day lag). Findings indicate that Twitter sentiment is directly correlated and can be predictive of the future prices of cryptocurrencies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Granger non-causality requires that past information of one time series does not alter the conditional distribution of another time series i.e. where Granger causality fails to reject the null hypothesis.
- 2.
- 3.
References
AliciaAdamczyk: What’s behind dogecoin’s price surge and why seemingly unrelated brands are capitalizing on its popularity (2021). https://www.cnbc.com/2021/05/12/dogecoin-price-surge-elon-musk-slim-jim.html
Bilen, M., Yilanci, V., Eryüzlü, H.: Tourism development and economic growth: a panel granger causality analysis in the frequency domain. Curr. Issue Tour. 20(1), 27–32 (2017)
Bollen, J., Mao, H., Zeng, X.: Twitter mood predicts the stock market. J. Comput. Sci. 2(1), 1–8 (2011). https://doi.org/10.1016/j.jocs.2010.12.007
Brooks, C.: What is statistical analysis? (2020). https://www.businessnewsdaily.com/6000-statistical-analysis.html
Chen, J., Becken, S., Stantic, B.: Lexicon based Chinese language sentiment analysis method. Comput. Sci. Inf. Syst. 16(2), 639–655 (2019)
Chuang, C.C., Kuan, C.M., Lin, H.Y.: Causality in quantiles and dynamic stock return-volume relations. J. Bank. Financ. 33(7), 1351–1360 (2009). https://doi.org/10.1016/j.jbankfin.2009.02.013
Cohen, M.X.: Analyzing Neural Time Series Data: Theory and Practice. MIT press, Cambridge (2014)
Wikimedia Commons: File:GrangerCausalityIllustration.svg (2014). https://commons.wikimedia.org/wiki/File:GrangerCausalityIllustration.svg
Dillard, J.: 5 most important methods for statistical data analysis (2015). https://www.bigskyassociates.com/blog/bid/356764/5-Most-Important-Methods-For-Statistical-Data-Analysis
Encyclopedia: International encyclopedia of the social sciences (2021). https://www.encyclopedia.com/social-sciences/applied-and-social-sciences-magazines/autoregressive-models
Granger, C.W.: Investigating causal relations by econometric models and cross-spectral methods. J. Econom. Soc. 37, 424–438 (1969)
Hagenau, M., Liebmann, M., Neumann, D.: Automated news reading: stock price prediction based on financial news using context-capturing features. Decis. Support Syst. 55(3), 685–697 (2013). https://doi.org/10.1016/j.dss.2013.02.006
Hendry, D., Teräsvirta, T.: Sir Clive William John Granger 1934–2009. Biogr. Mem. Fellows Br. Acad. 12, 451–469 (2013)
Hutto, C., Gilbert, E.: VADER: a parsimonious rule-based model for sentiment analysis of social media text. In: Proceedings of the International AAAI Conference on Web and Social Media, vol. 8, pp. 216–225 (2014)
Skare, M., Porada-Rochoń, M.: Financial and economic development link in transitional economies: a spectral granger causality analysis 1991–2017. Oecon. Copernic. 10(1), 7–35 (2019)
Tsen, W.H.: Exports, domestic demand, and economic growth in China: Granger causality analysis. Rev. Dev. Econ. 14(3), 625–639 (2010)
Wei, W.: Granger causality test (2016). https://www.sciencedirect.com/topics/social-sciences/granger-causality-test
You, W., Guo, Y., Peng, C.: Twitter’s daily happiness sentiment and the predictability of stock returns. Financ. Res. Lett. 23, 58–64 (2017). https://doi.org/10.1016/j.frl.2017.07.018
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
John, D.L., Stantic, B. (2022). Forecasting Cryptocurrency Price Fluctuations with Granger Causality Analysis. In: Szczerbicki, E., Wojtkiewicz, K., Nguyen, S.V., Pietranik, M., Krótkiewicz, M. (eds) Recent Challenges in Intelligent Information and Database Systems. ACIIDS 2022. Communications in Computer and Information Science, vol 1716. Springer, Singapore. https://doi.org/10.1007/978-981-19-8234-7_16
Download citation
DOI: https://doi.org/10.1007/978-981-19-8234-7_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8233-0
Online ISBN: 978-981-19-8234-7
eBook Packages: Computer ScienceComputer Science (R0)