Analyzing Bitcoin Price Trends: News Sentiment and Financial Metrics

Bitcoin (BTC) is a digital currency that is gaining popularity day by day, capturing the attention of investors, analysts, and researchers due to its volatile nature and the potential for high returns. However, the prices of cryptocurrencies like BTC are susceptible to significant fluctuations and risks. As a result, the prediction of Bitcoin price movements is increasingly crucial for both individuals and organizations. Hence, in this study, two datasets are constructed where the first dataset only includes news headlines and sentiment scores while the second one incorporates additional financial metrics. Both of the datasets are trained using Logistic Regression (LR), Random Forest (RF) and Support Vector Machine (SVM) models. Accordingly, results yield that SVM model performs the best for the sentiment only dataset, whereas RF model performs the best for the dataset with financial metrics. Furthermore, the model with the financial indicators performs better classification.