Predicting Bitcoin Price using Influential Tweets Sentiment and Supervised Learning

Abstract

Predicting cryptocurrency prices has become increasingly challenging due to their limited trading history and pronounced price volatility. Similar to traditional stock markets, where investor sentiment is significantly influenced by news and social media interactions, Twitter has recently emerged as a prominent indicator of Bitcoin price movements. This study investigates the influence of notable tweets on Bitcoin price fluctuations. In this paper, we present a method to extract hourly and daily impactful tweets related to Bitcoin by leveraging the Twitter network's topology. Furthermore, we propose a Bitcoin price prediction approach that consists of (a) a Twitter sentiment index model, constructed using data from influential tweets, and (b) a time-series XGBoosting model utilising Bitcoin price features derived from historical price data. Through an experimental evaluation, conducted on a substantial dataset comprising 1.8 million tweets, 400k Twitter users, and two months of Bitcoin price data, our model demonstrated superior performance, achieving a MAPE of 0.56%, an R-Square value of 0.99, a Pearson Correlation Coefficient of 0.99, and a Direction Accuracy of 92.06%. Based on the feature importance analysis of our model, we identify that the sentiment index and Bitcoin trade volume wield significant influence over Bitcoin price dynamics. The two-month time range may limit generalization to other market conditions.