Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction
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 se...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Risks |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9091/11/9/159 |
| _version_ | 1797577099671764992 |
|---|---|
| author | Vladyslav Koltun Ivan P. Yamshchikov |
| author_facet | Vladyslav Koltun Ivan P. Yamshchikov |
| author_sort | Vladyslav Koltun |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T22:04:11Z |
| format | Article |
| id | doaj.art-4d9d0241b1d9483d9bc57d451380493e |
| institution | Directory Open Access Journal |
| issn | 2227-9091 |
| language | English |
| last_indexed | 2024-03-10T22:04:11Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Risks |
| spelling | doaj.art-4d9d0241b1d9483d9bc57d451380493e2023-11-19T12:51:17ZengMDPI AGRisks2227-90912023-09-0111915910.3390/risks11090159Pump It: Twitter Sentiment Analysis for Cryptocurrency Price PredictionVladyslav Koltun0Ivan P. Yamshchikov1Instituto Superior de Economia e Gestao, University of Lisbon, 1200-781 Lisbon, PortugalTHWS, CAIRO, 97082 Würzburg, GermanyThis 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.https://www.mdpi.com/2227-9091/11/9/159cryptocurrencysentiment analysistwitter |
| spellingShingle | Vladyslav Koltun Ivan P. Yamshchikov Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction Risks cryptocurrency sentiment analysis |
| title | Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction |
| title_full | Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction |
| title_fullStr | Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction |
| title_full_unstemmed | Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction |
| title_short | Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction |
| title_sort | pump it twitter sentiment analysis for cryptocurrency price prediction |
| topic | cryptocurrency sentiment analysis |
| url | https://www.mdpi.com/2227-9091/11/9/159 |
| work_keys_str_mv | AT vladyslavkoltun pumpittwittersentimentanalysisforcryptocurrencypriceprediction AT ivanpyamshchikov pumpittwittersentimentanalysisforcryptocurrencypriceprediction |