Bridging Social Media and Cryptocurrency: A Deep Learning-Based Twitter Sentiment Analysis for Bitcoin Market

This manuscript explored a novel approach to forecasting Bitcoin market prices by leveraging user opinions on Twitter, using deep learning and word embedding models. We employed advanced techniques like Long Short-Term Memory Networks (LSTM), Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), and Recurrent Neural Networks (RNN) to analyze the relationship between Twitter sentiment and Bitcoin price dynamics. By aggregating daily Twitter data for sentiment scoring and aligning it with Bitcoin market trends, we explored the influence of social media on cryptocurrency markets. Our models were rigorously evaluated using Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Squared Error (RMSE). The findings indicate that the RNN model outperforms others, showcasing lower error rates and higher predictive accuracy. We also made a prophetic forecasting model. By systematically analyzing tweets related to Bitcoin, this research not only establishes a strong link between social media sentiment and Bitcoin market movements but also sets a foundation for future studies to further refine these predictive models, highlighting the importance of sentiment analysis in market forecasting.