Machine Learning based Cryptocurrency Price Prediction using historical data and Social Media Sentiment

Conference paper


Bhatt, S., Ghazanfar, M. and Amirhosseini, M. 2023. Machine Learning based Cryptocurrency Price Prediction using historical data and Social Media Sentiment . 5th International Conference on Machine Learning & Applications (CMLA 2023). Sydney, Australia 17 - 18 Jun 2023 AIRCC Publishing Corporation.
AuthorsBhatt, S., Ghazanfar, M. and Amirhosseini, M.
TypeConference paper
Abstract

The purpose of this research is to investigate the impact of social media sentiments on predicting the Bitcoin price using machine learning models, with a focus on integrating on-chain data and employing a Multi Modal Fusion Model. For conducting the experiments, the crypto market data, on-chain data, and corresponding social media data (Twitter) has been collected from 2014 to 2022 containing over 2000 samples. We trained various models over historical data including K-Nearest Neighbors, Logistic Regression, Gaussian Naive Bayes, Support Vector Machine, Extreme Gradient Boosting and a Multi Modal Fusion. Next, we added Twitter sentiment data to the models, using the Twitter-roBERTa and VADAR models to analyse the sentiments expressed in social media about Bitcoin. We then compared the performance of these models with and without the Twitter sentiment data and found that the inclusion of sentiment feature resulted in consistently better performance, with Twitter-RoBERTa-based sentiment giving an average F1 scores of 0.79. The best performing model was an optimised Multi Modal Fusion classifier using Twitter-RoBERTa based sentiment, producing an F1 score of 0.85. This study represents a significant contribution to the field of financial forecasting by demonstrating the potential of social media sentiment analysis, on-chain data integration, and the application of a Multi Modal Fusion model to improve the accuracy and robustness of machine learning models for predicting market trends, providing a valuable tool for investors, brokers, and traders seeking to make informed decisions.

KeywordsCryptocurrency; Bitcoin Price; Social Media; Sentiment Analysis; Machine Learning; K-Nearest Neighbors; Logistic regression; Gaussian Naive Bayes; Support Vector Machine; Extreme Gradient Boosting; Multi Modal Fusion
Year2023
Conference5th International Conference on Machine Learning & Applications (CMLA 2023)
PublisherAIRCC Publishing Corporation
Accepted author manuscript
License
File Access Level
Anyone
Publication process dates
Accepted02 May 2023
Deposited11 May 2023
ISSN2231 - 5403
Book titleComputer Science Conference Proceedings in Computer Science & Information Technology (CS & IT)
Web address (URL) of conference proceedingshttps://airccse.org/cscp.html
Copyright holder© 2023, The Author(s)
Permalink -

https://repository.uel.ac.uk/item/8vz30

Download files

  • 30
    total views
  • 23
    total downloads
  • 1
    views this month
  • 1
    downloads this month

Export as

Related outputs

Forecasting Bitcoin Prices in the Context of the COVID-19 Pandemic Using Machine Learning Approaches
Sontakke, P., Jafari, F., Saeedi, M. and Amirhosseini, M. 2023. Forecasting Bitcoin Prices in the Context of the COVID-19 Pandemic Using Machine Learning Approaches. 4th International Conference on Data Analytics & Management (ICDAM-2023). London, UK 23 - 24 Jun 2023 Springer.
A Machine Learning Approach to Identify the Preferred Representational System of a Person
Amirhosseini, M. and Wall, J. 2022. A Machine Learning Approach to Identify the Preferred Representational System of a Person. Multimodal Technologies and Interaction. 6 (12), p. 112. https://doi.org/10.3390/mti6120112
Application of Graph-Based Technique to Identity Resolution
Kazemian, H., Amirhosseini, M. H. and Phillips, M. 2022. Application of Graph-Based Technique to Identity Resolution. AIAI 2022: 18th International Conference on Artificial Intelligence Applications and Innovations. Crete, Greece 17 - 20 Jun 2022 Springer. https://doi.org/10.1007/978-3-031-08333-4_38
A novel DeepMaskNet model for face mask detection and masked facial recognition
Ullah, N., Javed, A., Ghazanfar, M., Alsufyani, A. and Bourouis, S. 2022. A novel DeepMaskNet model for face mask detection and masked facial recognition. Journal of King Saud University - Computer and Information Sciences. 30 (10-B), pp. 9905-9914. https://doi.org/10.1016/j.jksuci.2021.12.017
Asset Criticality and Risk Prediction for an Effective Cyber Security Risk Management of Cyber Physical System
Kure, H. I., Islam, S., Ghazanfar, M., Raza, A. and Pasha, M. 2021. Asset Criticality and Risk Prediction for an Effective Cyber Security Risk Management of Cyber Physical System. Neural Computing and Applications. 34, p. 493–514. https://doi.org/10.1007/s00521-021-06400-0
Novel online Recommendation algorithm for Massive Open Online Courses (NoR-MOOCs)
Khalid, A., Lundqvist, K., Yates, A. and Ghazanfar, M. 2021. Novel online Recommendation algorithm for Massive Open Online Courses (NoR-MOOCs). PLOS ONE. 16 (Art. e0245485). https://doi.org/10.1371/journal.pone.0245485
Identifying Users with Wearable Sensors based on Activity Patterns
Ehatisham-ul-Haq, M., Malik, M. N., Azam, M. A., Naeem, U., Khalid, A. and Ghazanfar, M. 2020. Identifying Users with Wearable Sensors based on Activity Patterns. The 11th International Conference on Emerging Ubiquitous Systems and Pervasive Networks (EUSPN 2020). Madeira, Portugal 02 - 05 Nov 2020 Elsevier. https://doi.org/10.1016/j.procs.2020.10.005
A Rule and Graph-Based Approach for Targeted Identity Resolution on Policing Data
Phillips, M., Amirhosseini, M. and Kazemian, H. 2020. A Rule and Graph-Based Approach for Targeted Identity Resolution on Policing Data. 2020 IEEE Symposium Series on Computational Intelligence. Online 01 - 04 Dec 2020 IEEE. https://doi.org/10.1109/SSCI47803.2020.9308182
Machine Learning Approach to Personality Type Prediction Based on the Myers–Briggs Type Indicator®
Amirhosseini, M.H. and Kazemian, H. 2020. Machine Learning Approach to Personality Type Prediction Based on the Myers–Briggs Type Indicator®. Multimodal Technologies and Interaction. 4 (Art. 9). https://doi.org/10.3390/mti4010009
Modeling user rating preference behavior to improve the performance of the collaborative filtering based recommender systems
Ayub, M., Ghazanfar, M., Mehmood, Z., Saba, T., Alharbey, R., Munshi, A. M. and Alrige, M. A. 2019. Modeling user rating preference behavior to improve the performance of the collaborative filtering based recommender systems. PLOS ONE. 14 (Art. e0220129). https://doi.org/10.1371/journal.pone.0220129
Automating the process of identifying the preferred representational system in Neuro Linguistic Programming using Natural Language Processing
Amirhosseini, M.H. and Kazemian, H. 2019. Automating the process of identifying the preferred representational system in Neuro Linguistic Programming using Natural Language Processing. Cognitive Processing. 20 (2), p. 175–193. https://doi.org/10.1007/s10339-019-00912-3
Kernel Context Recommender System (KCR): A Scalable Context-Aware Recommender System Algorithm
Iqbal, Misbah, Ghazanfar, M., Sattar, Asma, Maqsood, Muazzam, Khan, Salabat, Mehmood, Irfan and Baik, Sung Wook 2019. Kernel Context Recommender System (KCR): A Scalable Context-Aware Recommender System Algorithm. IEEE Access. 7, pp. 24719-24737. https://doi.org/10.1109/ACCESS.2019.2897003
Natural Language Processing approach to NLP Meta model automation
Amirhosseini, M.H., Kazemian, H., Ouazzane, K. and Chandler, C. 2018. Natural Language Processing approach to NLP Meta model automation. 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro, Brazil 08 - 13 Jul 2018 IEEE. https://doi.org/10.1109/IJCNN.2018.8489609
A Robust Regression-Based Stock Exchange Forecasting and Determination of Correlation between Stock Markets
Khan, U., Aadil, F., Ghazanfar, M., Khan, S., Metawa, N., Muhammad, K., Mehmood, I. and Nam, Y. 2018. A Robust Regression-Based Stock Exchange Forecasting and Determination of Correlation between Stock Markets. Sustainability. 10 (Art. 3702). https://doi.org/10.3390/su10103702