DOI: 10.5121/csit.2023.130302

Cryptocurrency Price Prediction using Twitter Sentiment Analysis

Haritha GBSahana N.B

Mar 2023

摘要

The cryptocurrency ecosystem has been the centre of discussion on many socialmedia platforms, following its noted volatility and varied opinions. Twitter israpidly being utilised as a news source and a medium for bitcoin discussion.Our algorithm seeks to use historical prices and sentiment of tweets toforecast the price of Bitcoin. In this study, we develop an end-to-end modelthat can forecast the sentiment of a set of tweets (using a BidirectionalEncoder Representations from Transformers - based Neural Network Model) andforecast the price of Bitcoin (using Gated Recurrent Unit) using the predictedsentiment and other metrics like historical cryptocurrency price data, tweetvolume, a user's following, and whether or not a user is verified. Thesentiment prediction gave a Mean Absolute Percentage Error of 9.45%, an averageof real-time data, and test data. The mean absolute percent error for the priceprediction was 3.6%.

展开全部

图表提取