This paper explores the application of sentiment analysis and machine learning techniques to predict daily cryptocurrency price returns. The study finds that social media sentiment related to Bitcoin does not significantly predict price returns for cryptocurrencies. Machine learning models that assume linearity between price returns and sentiment scores were less accurate than models that do not assume linearity. The VADER sentiment analysis tool was used to compute sentiment scores of tweets, and LSTM neural networks were used to predict cryptocurrency prices. The study also highlights the impact of public sentiment on stock and cryptocurrency prices.
Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.