Cryptocurrency Price Prediction using Forecasting and Sentiment Analysis

In recent years, many investors have used cryptocurrencies, prompting specialists to find out the factors that affect cryptocurrencies’ prices. Therefore, one of most popular methods been predict cryptocurrency prices is sentiment analysis. It a widespread technique utilized by researchers on social media platforms, particularly Twitter. Thus, determine relationship between investors’ and volatility prices, this study forecasts using Long-Term-Short-Memory (LSTM) deep learning algorithm. addition, Twitter users’ sentiments Support Vector Machine (SVM) Naive Bayes (NB) machine approaches are analyzed. As result, in classification bitcoin (BTC) Ethereum (ETH) datasets into (Positive, Negative, Neutral), SVM algorithm outperformed NB with an accuracy 93.95% 95.59%, respectively. Furthermore, forecasting regression model achieves error rate 0.2545 for MAE, 0.2528 MSE, 0.5028 RMSE.