Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction

Author:

Koltun Vladyslav1,Yamshchikov Ivan P.23ORCID

Affiliation:

1. Instituto Superior de Economia e Gestao, University of Lisbon, 1200-781 Lisbon, Portugal

2. THWS, CAIRO, 97082 Würzburg, Germany

3. CEMAPRE, University of Lisbon, 1649-004 Lisbon, Portugal

Abstract

This study demonstrates the significant impact of market sentiment, derived from social media, on the daily price prediction of cryptocurrencies in both bull and bear markets. Through the analysis of approximately 567 thousand tweets related to twelve specific cryptocurrencies, we incorporate the sentiment extracted from these tweets along with daily price data into our prediction models. We test various algorithms, including ordinary least squares regression, long short-term memory network and neural hierarchical interpolation for time series forecasting (NHITS). All models show better performance once the sentiment is incorporated into the training data. Beyond merely assessing prediction error, we scrutinise the model performances in a practical setting by applying them to a basic trading algorithm managing three distinct portfolios: established tokens, emerging tokens, and meme tokens. While NHITS emerged as the top-performing model in terms of prediction error, its ability to generate returns is not as compelling.

Publisher

MDPI AG

Subject

Strategy and Management,Economics, Econometrics and Finance (miscellaneous),Accounting

Reference24 articles.

1. Cryptocurrency price prediction using tweet volumes and sentiment analysis;Abraham;SMU Data Science Review,2018

2. Cabanilla, Kurt Izak M. (2023, January 01). The Future of Cryptocurrency: Forecasting the Bitcoin-Philippine Peso Exchange Rate Using Sarima through Tramo-Seats. Available online: https://www.academia.edu/31926493/The_Future_of_Cryptocurrency_Forecasting_The_Bitcoin_Philippine_Peso_Exchange_Rate_Using_SARIMA_Through_TRAMO_SEATS.

3. N-hits: Neural hierarchical interpolation for time series forecasting;Challu;Proceedings of the AAAI Conference on Artificial Intelligence,2022

4. Algorithmic trading of cryptocurrency based on twitter sentiment analysis;Colianni;CS229 Project,2015

5. Dwivedi, DwijendraNath, and Vemareddy, Anilkumar (, January January). Sentiment analytics for crypto pre and post covid: Topic modeling. Paper presented at Distributed Computing and Intelligent Technology: 19th International Conference, ICDCIT 2023, Bhubaneswar, India.

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3