Machine Learning for Prediction of Emotion Towards Digital Assets

The article discusses the use of machine learning algorithms for Bitcoin sentiment analysis to predict market movements and guide financial decisions. It explains how machine learning can be used for sentiment classification and trend forecasting, and the different methods currently in use. The review of the extant literature on the topic has used machine learning algorithms to forecast Bitcoin prices based on social media sentiment and technical analysis. The article used a multimethod approach utilizing six methods, namely Naïve Bayes, K -Nearest Neighbour, XGBoost, Random Forest, Decision Tree, and Support Vector Machine. The results of the experiments found that Random Forest, Decision Tree, and Support Vector Machine are the superior models for predicting the bitcoin movement using historical price data having sentiments such as positive and negative views. This dataset is used to demonstrate the suggested sentiment analysis method for uncertain economic circumstances, and it may be adapted to fit different settings in the same way. The article concludes that machine learning can accurately predict Bitcoin price shifts and sentiment changes, but the interpretability and reliability of the models must be considered.