CFP last date
15 October 2024
Call for Paper
November Edition
IJAIS solicits high quality original research papers for the upcoming November edition of the journal. The last date of research paper submission is 15 October 2024

Submit your paper
Know more
Reseach Article

Bitcoin Price Prediction using Tweet Sentiment and User Interaction Behaviour

by Qinan Zhu, Rotimi Ogunsakin, Laud Charles Ochei
International Journal of Applied Information Systems
Foundation of Computer Science (FCS), NY, USA
Volume 12 - Number 43
Year of Publication: 2024
Authors: Qinan Zhu, Rotimi Ogunsakin, Laud Charles Ochei
10.5120/ijais2024451967

Qinan Zhu, Rotimi Ogunsakin, Laud Charles Ochei . Bitcoin Price Prediction using Tweet Sentiment and User Interaction Behaviour. International Journal of Applied Information Systems. 12, 43 ( Apr 2024), 23-35. DOI=10.5120/ijais2024451967

@article{ 10.5120/ijais2024451967,
author = { Qinan Zhu, Rotimi Ogunsakin, Laud Charles Ochei },
title = { Bitcoin Price Prediction using Tweet Sentiment and User Interaction Behaviour },
journal = { International Journal of Applied Information Systems },
issue_date = { Apr 2024 },
volume = { 12 },
number = { 43 },
month = { Apr },
year = { 2024 },
issn = { 2249-0868 },
pages = { 23-35 },
numpages = {9},
url = { https://www.ijais.org/archives/volume12/number43/bitcoin-price-prediction-using-tweet-sentiment-and-user-interaction-behaviour/ },
doi = { 10.5120/ijais2024451967 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-04-29T11:40:43+05:30
%A Qinan Zhu
%A Rotimi Ogunsakin
%A Laud Charles Ochei
%T Bitcoin Price Prediction using Tweet Sentiment and User Interaction Behaviour
%J International Journal of Applied Information Systems
%@ 2249-0868
%V 12
%N 43
%P 23-35
%D 2024
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Sentiment analysis has been used to predict Bitcoin prices, with results indicating relatively low prediction accuracy. User interaction behaviour such as likes, retweets, and replies have received little to no consideration as potential price prediction signals. Consequently, this paper uses both user interaction behaviour and Twitter sentiment to predict Bitcoin closing prices using multiple linear regression and Extreme Gradient Boosting (XGBoost). The predictive model outcomes are investigated using regression analysis and Shapley Additive Explanations (SHAP). Our findings indicate that using both sentiment score and user interaction behaviours significantly improves prediction accuracy, mostly during price volatility, but fails to capture Bitcoin price movement trends. Analysis of feature importance and impact on prediction outcome reveals sentiment score and user interaction behaviour play a lesser role in Bitcoin price prediction during price volatility. However, when Bitcoin prices are relatively stable, the improved accuracy is primarily due to the incorporation of user interaction behaviour. Therefore, the sentiment score is insufficient because the majority of Bitcoin-related tweets come from Bitcoin enthusiasts whose opinions are unaffected by market fluctuations. Whereas, the improved prediction accuracy observed during Bitcoin’s price volatility is attributable to increased interactions from new sets of users.

References
  1. Abraham, J., Higdon, D., Nelson, J. and Ibarra, J. (2018) Cryptocurrency Price Prediction Using Tweet Volumes and Sentiment Analysis. SMU Data Science Review: [online] 1(3) Available from: https://scholar.smu.edu/datasciencereview/vol1/iss3/1 [accessed 13 September 2021].
  2. Benevenuto, F., Rodrigues, T., Cha, M., & Almeida, V. (2009, November). Characterizing user behavior in online social networks. In Proceedings of the 9th ACM SIGCOMM Conference on Internet Measurement (pp. 49-62).
  3. Blasco, N., Corredor, P. and Ferreruela, S. (2012). Market sentiment: a key factor of investors’ imitative behaviour. Accounting & Finance, 52(3), 663-689.
  4. Bollen, J., Mao, H. and Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1-8.
  5. Colianni, S., Rosales, S., and Signorotti, M. (2015). Algorithmic Trading of Cryptocurrency Based on Twitter Sentiment Analysis.
  6. Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
  7. Contreras, J., Espinola, R., Nogales, F. and Conejo, A. (2003). ARIMA models to predict next-day electricity prices. IEEE Transactions on Power Systems, 18(3), 1014-1020.
  8. Galeshchuk, S., Vasylchyshyn, O., and Krysovatyy, A. (2018). Bitcoin Response to Twitter Sentiments. ICTERI Workshops.
  9. Garcia, D. and Schweitzer, F. (2015) Social signals and algorithmic trading of Bitcoin. Royal Society Open Science, 2(9).
  10. Gotz, D., Zhou, M. X. (2008). An empirical study of user interaction behavior during visual analysis. IBM Research RC24525 (W0803-127).
  11. Hutto, C., & Gilbert, E. (2014, May). 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, No. 1, pp. 216-225).
  12. Jahjah, F.H., and Rajab, M. (2020). Impact of Twitter Sentiment Related to Bitcoin on Stock Price Returns. The Journal of Engineering, 26, 60-71.
  13. Jain, A. (2016). Complete Guide to Parameter Tuning in XGBoost with codes in Python. [online] Available from: https://www.analyticsvidhya.com/blog/2016/03/complete-guideparameter-tuning-xgboost-with-codes-python/ [accessed 13 September 2021].
  14. Jain, A., Tripathi, S., Dwivedi, H. and Saxena, P. (2018). Forecasting Price of Cryptocurrencies using Tweets Sentiment Analysis. Proceedings of 2018 Eleventh International Conference on Contemporary Computing (IC3), Noida, India.
  15. Jang, H. and Lee, J. (2017). An Empirical Study on Modeling and Prediction of Bitcoin Prices with Bayesian Neural Networks Based on Blockchain Information. IEEE, 6, 5427-5437.
  16. Kahneman, D. and Tversky, A. (1979). Prospect Theory: An Analysis of Decision under Risk. Econometrica, 47(2), 263-292.
  17. Kaminski, J. (2014), Nowcasting the bitcoin market with twitter signals. MIT Media Lab [online] Available from: http://arxiv.org/abs/1406.7577 [accessed 13 September 2021].
  18. Kim, Y., Lee, J., Park, N., Choo, J., Kim, J. and Kim, C. (2017). When Bitcoin encounters information in an online forum: Using text mining to analyse user opinions and predict value fluctuation. PLOS ONE, 12(5), e0177630.
  19. Kraaijeveld, O., Smedt, J. (2020). The predictive power of public Twitter sentiment for forecasting cryptocurrency prices. Journal of International Financial Markets, Institutions & Money. 65, 101188.
  20. Li, T., Chamrajnagar, A., Fong, X., Rizik, N. and Fu, F. (2019). Sentiment-Based Prediction of Alternative Cryptocurrency Price Fluctuations Using Gradient Boosting Tree Model. Frontiers in Physics, 7(98).
  21. Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S. (2020). Explainable ai: A review of machine learning interpretability methods. Entropy, 23(1), 18.
  22. Madan, I., Saluja, S., & Zhao, A. (2015). Automated bitcoin trading via machine learning algorithms. URL: http://cs229. stanford.edu/proj2014/Isaac% 20Madan, 20.[accessed 12 January 2023].
  23. McNally, S., Roche, J. and Caton, S. (2018) Predicting the Price of Bitcoin Using Machine Learning. 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP). 339-343.
  24. Mohapatra, S., Ahmed, N. and Alencar, P. (2019). KryptoOracle: A RealTime Cryptocurrency Price Prediction Platform Using Twitter Sentiments. IEEE Big Data.
  25. Nakamoto, S. (2008). Bitcoin: A peer-to-peer electronic cash system. Decentralized Business Review, 21260.
  26. 2010)]con01 O’Connor, B., Balasubramanyan, R., Routledge, B. and Smith, N. (2010). From tweets to polls: Linking text sentiment to public opinion time series. Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, 122-129.
  27. Ozt¨ urk,¨ S., and Bilgic¸, M. (2021). Twitter & bitcoin: are the most influential accounts really influential?, Applied Economics Letters [online] Available from: https://doi.org/10.1080/13504851.2021.1904104 [accessed 13 September 2021].
  28. Pagolu, V., Challa, K., Panda, G. and Majhi, B. (2016). Sentiment Analysis of Twitter Data for Predicting Stock Market Movements. International conference on Signal Processing, Communication, Power and Embedded System (SCOPES). Paralakhemundi, India. 3th-5th October 2016.
  29. Panger, G.T. (2017) Emotion in Social Media. Ph.D. University of California, Berkeley.
  30. Ranco, G., Aleksovski, D., Caldarelli, G., Grcar, M., and Mozetiˇ c, I.ˇ (2015). The Effects of Twitter Sentiment on Stock Price Returns. PLoS ONE, 10 (9).
  31. Rao, T. and Srivastava, S. (2012) Analyzing Stock Market Movements Using Twitter Sentiment Analysis. Proceedings of the 2012 International Conference on Advances in Social Networks Analysis and Mining.
  32. Redman, J. (2019). Bitcoin Gained 8.9 Million Percent Over the Last Decade – Featured Bitcoin News. [online] Available from: https://news.bitcoin.com/bitcoin-gained-8-9-million-percent-over-the-lastdecade/ [accessed 13 September 2021].
  33. Redman, J. (2021). The 35 Most Influential Bitcoiners Dominating Crypto Twitter by Follower Count – Featured Bitcoin News. [online]. Available from: https://news.bitcoin.com/35-most-influentialbitcoin-crypto-twitter/ [accessed 13 September 2021].
  34. Runkevicius, D. (2021). Myth Busted: Institutional Investors Are Not Investing In Bitcoin [online] Available from:https://www.forbes.com/sites/danrunkevicius/2021/01/14/myth-bustedwall-street-is-not-investing-in-bitcoin/?sh=43efa1025510 [accessed 13 September 2021].
  35. Silverman, G., Murphy, H. and Authers, J. (2017). Bitcoin: an investment mania for the fake news era, [online] Financial Times. Available from: https://www.ft.com/content/c84caffc-d683-11e7-a303-9060cb1e5f44 [accessed 13 September 2021].
  36. Smales, L. (2017). The importance of fear: investor sentiment and stock market returns. Applied Economics, 49(34), 3395-3421.
  37. Sul, H., Dennis, A. and Yuan, L. (2016). Trading on Twitter: Using Social Media Sentiment to Predict Stock Returns. Decision Sciences, 48(3), 454-488.
  38. Tetlock, P. (2007). Giving Content to Investor Sentiment: The Role of Media in the Stock Market. The Journal of Finance, 62(3), 1139-1168.
  39. Verma, M. and Sharma, P. (2020). Money Often Costs Too Much: A Study to Investigate The Effect Of Twitter Sentiment On Bitcoin Price Fluctuation. Preprints [online] Available from: https://doi.org/10.20944/preprints202009.0216.v1 [accessed 13 September 2021].
  40. Weigel, Detlef, and Jane Glazebrook. 2002. Arabidopsis: A Laboratory Manual. Cold Spring Harbor, NY: Cold Spring Harbor Laboratory Press.
  41. Yermack, D. (2013). Is Bitcoin a Real Currency? An Economic Appraisal. NBER Working Paper, [online] 19747. Available from:
  42. http://www.nber.org/papers/w19747 [accessed 13 September 2021].
  43. Yu, J. and Yuan, Y. (2011). Investor sentiment and the mean–variance relation. Journal of Financial Economics, 100(2), 367-381.
  44. Zheludev, I., Smith, R. and Aste, T. (2014). When Can Social Media Lead Financial Markets? Scientific Reports, 4(1).
Index Terms

Computer Science
Information Sciences

Keywords

Sentiment analysis bitcoin price prediction explainable AI Twitter sentiment