Bitcoin prices and volatility predictions based on crawled data.

Abstract

The thesis analyses broadly the recent developments of the role of Bitcoin in Economics and Finance, exploring the role played by social media, the internet and big data. Subsequently, it proceeds in introducing relevant data crawling and sentiment analysis techniques; in particular the use of “VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text”. The thesis develops the study on “Predicting Fluctuations in Cryptocurrency Transactions Based on User Comments and Replies” by Kim YB et al.