Predicting bitcoin price movements using sentiment analysis: a machine learning approach

Abstract

Purpose Cryptocurrencies such as Bitcoin (BTC) attracted a lot of attention in recent months due to their unprecedented price fluctuations. This paper aims to propose a new method for predicting the direction of BTC price using linear discriminant analysis (LDA) together with sentiment analysis. Design/methodology/approach Concretely, the authors train an LDA-based classifier that uses the current BTC price information and BTC news announcements headlines to forecast the next-day direction of BTC prices. The authors compare the results with a Support Vector Machine (SVM) model and random guess approach. The use of BTC price information and news announcements related to crypto enables us to value the importance of these different sources and types of information. Findings Relative to the LDA results, the SVM model was more accurate in predicting BTC next day’s price movement. All models yielded better forecasts of an increase in tomorrow’s BTC price compared to forecasting a decrease in the crypto price. The inclusion of news sentiment resulted in the highest forecast accuracy of 0.585 on the test data, which is superior to a random guess. The LDA (SVM) model with asset specific (news sentiment and asset specific) input features ranked first within their respective model classifiers, suggesting both BTC news sentiment and asset specific are prized factors in predicting tomorrow’s price direction. Originality/value To the best of the authors’ knowledge, this is the first study to analyze the potential effect of crypto-related sentiment and BTC specific news on BTC’s price using LDA and sentiment analysis.

Exploring the relationship between digital trails of social signals and bitcoin returns

“…Another widely explored sub-stream of research in the domain is examining netizens’ thoughts and expectations regarding bitcoin price returns (e.g. Wołk, 2020; Hassan et al , 2022; Gurrib and Kamalov, 2022).…”

High Frequency Return and Risk Patterns in U.S. Sector ETFs during COVID-19

“…In stock prediction, a deep neural network together with a custom feature selection algorithm was employed by Long et al (2019) to predict the Chinese stock market index CSI 300. Gurrib and Kamalov (2021) compared a linear discriminant analysis model which includes sentiment analysis and asset specific information such as daily prices, with a support vector machine model, to predict tomorrow's price of bitcoin. A combination of the classical Auto Regressive Integrated Moving Average (ARIMA) model together with the modern neural networks was proposed by Sun et al (2019) to capture intra-day patterns for stock market shock forecasting.…”

Cross Cryptocurrency Relationship Mining for Bitcoin Price Prediction

“…Karalevicius et al [18] collected and studied the database of Bitcoin-related news and blogs, and the results show that there is an interaction between media sentiment and Bitcoin price. Gurrib [19] used linear discriminant analysis (LDA) and sentiment analysis to predict the trend of Bitcoin price fluctuation, and the results show that the LDA (SVM) model that considers both news sentiment and Bitcoin price information as input features achieves relatively good results. These studies have shown that external information is an important factor affecting the prediction of Bitcoin price.…”