Predicting the Price Direction of Bitcoin Using Twitter Data and Machine Learning

Bitcoin is a decentralized digital currency that was intro- duced in 2009 and since then, has become increasingly popular as one of the most known and highly valued currencies. Contributing factors to its rise include crypto Twitter influencers. An engaged audience on Twitter seems to have an influe...

Full description

Saved in:

Bibliographic Details
Published in:	2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) pp. 46 - 52
Main Authors:	Kanji, Abdul Mannan, Chaudhary, Ishita, Shankar, Rithika Lakshmi, Srinivasa, Gowri
Format:	Conference Proceeding
Language:	English
Published:	IEEE 28.10.2022
Subjects:	Bitcoin Blogs Candlestick plots Computational modeling Cryptocurrency Machine learning models Moon Online banking Price direction prediction Social networking (online) Support vector machine classification
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Bitcoin is a decentralized digital currency that was intro- duced in 2009 and since then, has become increasingly popular as one of the most known and highly valued currencies. Contributing factors to its rise include crypto Twitter influencers. An engaged audience on Twitter seems to have an influence on the cryptocurrency market. In this paper, we analyze the impact that tweets have on the price of Bitcoin. Using word-clouds and candlestick plots, we gain insight into the factors that affect Bitcoin prices. We also use various machine learning techniques to automatically classify the sentiment in Tweets related to cryptocurrencies. We incorporate these and other relevant features to build and compare the performance of multiple machine learning models to predict the direction (increase or decrease) of the price of Bitcoin.
DOI:	10.1109/ICDSCA56264.2022.9988558