Enhancing Bitcoin Price Prediction with Deep Learning: Integrating Social Media Sentiment and Historical Data
Source abstract
Abstract
Bitcoin, the pioneering cryptocurrency, is renowned for its extreme volatility and speculative nature, making accurate price prediction a persistent challenge for investors. While recent studies have employed multivariate models to integrate historical price data with social media sentiment analysis, this study focuses on improving an existing univariate approach By incorporating sentiment and tweet volume data into a multivariate framework, we systematically evaluated the benefits of this integration. Among the five LSTM-based models developed for this study, the Multi-LSTM-Sentiment model achieved the best performance, with the lowest mean absolute error (MAE) of 0.00196 and root-mean-square error (RMSE) of 0.00304. These results underscore the significance of including social media sentiment in predictive modelling and demonstrate its potential to enhance decision-making in the highly dynamic cryptocurrency market.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Blockchain Technology Applications and Security · Stock Market Forecasting Methods · Sentiment Analysis and Opinion Mining
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computing, University of Portsmouth, Buckingham Building, Lion Terrace, Portsmouth PO1 3HE, UK
References (21)
Show source-provided references
1. Harvey, C.R. (2014). Bitcoin Myths and Facts. SSRN Electron. J.10.2139/ssrn.2479670 ↗
2. Edwards, J., Mansa, J., and Kvilhaug, S. (2024, December 01). Bitcoin’s Price History. Investopedia, 2023. Available online: https://www.investopedia.com/articles/forex/121815/bitcoins-price-history.asp.
3. Popper, N. (2015). Digital Gold: The Untold Story of Bitcoin, Penguin Books UK.
4. Hochreiter, S. (1997). Long Short-Term Memory. Neural Computation, MIT Press.10.1162/neco.1997.9.8.1735 ↗
5. Text mining and emotion classification on monkeypox Twitter dataset: A deep learning-natural language processing (NLP) approach10.1109/ACCESS.2023.3277868 ↗
6. Brownlee, J. (2024, December 01). Multivariate Time Series Forecasting with LSTMs in Keras. Available online: https://machinelearningmastery.com/multivariate-time-series-forecasting-lstms-keras/.
7. Twitter Sentiment Analysis and Bitcoin Price Forecasting: Implications for Financial Risk Management10.1108/JRF-09-2023-0241 ↗
8. Media Attention and Bitcoin Prices10.1016/j.frl.2019.03.031 ↗
9. Cryptocurrency Price Prediction Using Tweet Volumes and Sentiment Analysis
10. Gu, W.J., Zhong, Y.H., Li, S.Z., Wei, C.S., Dong, L.T., Wang, Z.Y., and Yan, C. (2024, January 15–17). Predicting Stock Prices with FinBERT-LSTM: Integrating News Sentiment Analysis. Proceedings of the 2024 8th International Conference on Cloud and Big Data Computing, Oxford, UK.
11. Kehinde, T.O., Khan, W.A., and Chung, S.H. (2023, January 10–12). Financial Market Forecasting Using RNN, LSTM, BiLSTM, GRU and Transformer-Based Deep Learning Algorithms. Proceedings of the IEOM International Conference on Smart Mobility and Vehicle Electrification, Detroit, MI, USA.10.46254/EV01.20230037 ↗
12. Sangwan, V., Kumar, V., and Christopher, V.B. (2024). Contrasting the Efficiency of Stock Price Prediction Models Using Various Types of LSTM Models Aided with Sentiment Analysis. AIP Conference Proceedings, AIP Publishing.10.1063/5.0217470 ↗
13. HyBiLSTM: Multivariate Bitcoin Price Forecasting Using Hybrid Time-Series Models With Bidirectional LSTM10.1109/ACCESS.2024.3386029 ↗
14. Zuvela, T., Lazarevic, S., Djordjevic, S., Arsenovic, M., and Sladojevic, S. (2022, January 25–28). Cryptocurrency Price Prediction Using Deep Learning. Proceedings of the 2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI), Timisoara, Romania.10.1109/SACI55618.2022.9919554 ↗
15. Pattanayak, S. (2023). Pro Deep Learning with TensorFlow 2.0: A Mathematical Approach to Advanced Artificial Intelligence in Python, Apress L.P.. [2nd ed.].10.1007/978-1-4842-8931-0 ↗
16. IBM (2024, December 01). What Is a Recurrent Neural Network (RNN)?. Available online: https://www.ibm.com/think/topics/recurrent-neural-networks.
17. Mudassir, M., Bennbaia, S., Unal, D., and Hammoudeh, M. (2020). Time-Series Forecasting of Bitcoin Prices Using High-Dimensional Features: A Machine Learning Approach. Neural Computing and Applications, Springer.10.1007/s00521-020-05129-6 ↗
18. Bitcoin Price Change and Trend Prediction Through Twitter Sentiment and Data Volume10.1186/s40854-022-00352-7 ↗
19. Seabe, P.L., Moutsinga, C.R.B., and Pindza, E. (2023). Forecasting Cryptocurrency Prices Using LSTM, GRU, and Bi-Directional LSTM: A Deep Learning Approach. Fractal Fract., 7.10.3390/fractalfract7020203 ↗
20. Janssens, J. (2021). Data Science at the Command Line, O’Reilly Media. [2nd ed.].
21. Exploreai, and Data and Sons (2024, December 01). Bitcoin Tweets and Price Dataset. Available online: https://www.dataandsons.com/categories/markets/bitcoin-tweets-dataset-2017-to-2019.