New Paper Explores Social Media's Influence on Cryptocurrency Prices

06.09.2023 | thws.de, CAIRO

In the field of cryptocurrency analysis, CAIRO Research Professor Prof Dr Ivan Yamshchikov has published a new paper together with Vladyslav Koltun from the Instituto Superior de Economia e Gestao, University of Lisbon, showing the impact of social media on the daily price prediction of cryptocurrencies. The paper, titled "Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction", highlights how sentiment from about half a million tweets influences the predictive models.

The abstract reads as follows:
“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.”
(Koltun V, Yamshchikov IP. Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction. Risks. 2023; 11(9):159. doi.org/10.3390/risks11090159)

The full paper can be found under the following link: https://www.mdpi.com/2227-9091/11/9/159


Keywords: cryptocurrency; sentiment analysis; twitter