Sentiment analysis involves the method of extracting opinions, emotions, and attitudes from the text data to derive meaningful insights. Integrating sentiment analysis into cryptocurrency markets can provide a broader perspective on market dynamics by capturing real-time public sentiment. However, traditional Bitcoin price prediction models often overlook the influence of social media sentiments, leading to incomplete predictions. The developed model proposes a solution that combines historical market data with public sentiments to forecast Bitcoin prices. The historical price data is collected from Yahoo Finance and social media sentiments are extracted from tweets. The GRU model is used for predicting as it effectively captures long-term dependencies in time-series data and outperforms traditional models like Linear Regression, ARIMA, and Random Forests. The evaluation of the model’s performance is conducted using metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and accuracy to show significance of integrating sentiment analysis for improving prediction accuracy.