Sentiment Analysis of Bitcoin data by tweets through Naive Bayes

Abstract

Bitcoin, as one of the most popular cryptocurrencies, is notorious for its concerning volatility on any given day, which leads to people having mixed feelings about it. This paper examines the opinions of people all over the world using data gathered from the social media platform Twitter, to decide if investing in bitcoin is a good idea for future. The opinions are analyzed and classified using the Bernoulli and Multinomial Naive Bayes model through sentiment analysis, the models implemented yielded 87 and 86 percent of accuracies respectively. Furthermore, the variation in sentiment over time is comparedto the variation in bitcoin price over the same period.