Short-Term Bitcoin Price Fluctuation Prediction Using Social Media and Web Search Data

Abstract

In recent years, the social network has been widely used among the public to share their views and for communication as well. Further, sentiments of the text used in emails, blogs, and social media posts affect human decision making and behavior. Bitcoin being a decentralized and peer-to-peer cryptocurrency has attracted a large number of users on the web search and social media. The goal of this paper is to correlation among Bitcoin price and Twitter and Google search patterns. Linear regression, polynomial regression, Recurrent Neural Network, and Long Short Term Memory based analysis concludes that there is a relevant degree of correlation of Google Trends and Tweet volume data with the price of Bitcoin, and with no significant relation with the sentiments of tweets.