Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Exploring Relationships Between Cryptocurrency News Outlets and Influencers' Twitter Activity and Market Prices

Meysam Alizadeh, Yasaman Asgari, Zeynab Samei, Sara Yari, Shirin Dehghani, Mael Kubli, Darya Zare, Juan Diego Bermeo, Veronika Batzdorfer, Fabrizio Gilardi

TL;DR

LLMs are used to uncover buy and not-buy signals from influencers and news outlets' Twitter posts and a VAR analysis with Granger Causality tests and cross-correlation analysis to understand how these trading signals are temporally correlated with the top nine major cryptocurrencies' prices.

Abstract

Academics increasingly acknowledge the predictive power of social media for a wide variety of events and, more specifically, for financial markets. Anecdotal and empirical findings show that cryptocurrencies are among the financial assets that have been affected by news and influencers' activities on Twitter. However, the extent to which Twitter crypto influencer's posts about trading signals and their effect on market prices is mostly unexplored. In this paper, we use LLMs to uncover buy and not-buy signals from influencers and news outlets' Twitter posts and use a VAR analysis with Granger Causality tests and cross-correlation analysis to understand how these trading signals are temporally correlated with the top nine major cryptocurrencies' prices. Overall, the results show a mixed pattern across cryptocurrencies and temporal periods. However, we found that for the top three cryptocurrencies with the highest presence within news and influencer posts, their aggregated LLM-detected trading signal over the preceding 24 hours granger-causes fluctuations in their market prices, exhibiting a lag of at least 6 hours. In addition, the results reveal fundamental differences in how influencers and news outlets cover cryptocurrencies.

Exploring Relationships Between Cryptocurrency News Outlets and Influencers' Twitter Activity and Market Prices

TL;DR

LLMs are used to uncover buy and not-buy signals from influencers and news outlets' Twitter posts and a VAR analysis with Granger Causality tests and cross-correlation analysis to understand how these trading signals are temporally correlated with the top nine major cryptocurrencies' prices.

Abstract

Academics increasingly acknowledge the predictive power of social media for a wide variety of events and, more specifically, for financial markets. Anecdotal and empirical findings show that cryptocurrencies are among the financial assets that have been affected by news and influencers' activities on Twitter. However, the extent to which Twitter crypto influencer's posts about trading signals and their effect on market prices is mostly unexplored. In this paper, we use LLMs to uncover buy and not-buy signals from influencers and news outlets' Twitter posts and use a VAR analysis with Granger Causality tests and cross-correlation analysis to understand how these trading signals are temporally correlated with the top nine major cryptocurrencies' prices. Overall, the results show a mixed pattern across cryptocurrencies and temporal periods. However, we found that for the top three cryptocurrencies with the highest presence within news and influencer posts, their aggregated LLM-detected trading signal over the preceding 24 hours granger-causes fluctuations in their market prices, exhibiting a lag of at least 6 hours. In addition, the results reveal fundamental differences in how influencers and news outlets cover cryptocurrencies.

Paper Structure

This paper contains 24 sections, 4 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Effect of Sentiment on Financial Markets
  4. Twitter Sentiment Analysis
  5. Twitter and Cryptocurrency Market
  6. Limitations of Current Literature
  7. Methods and Data
  8. Twitter Data
  9. Cryptocurrency Data
  10. Twitter Data Pre-processing
  11. Influencer Identification
  12. Trading Signal Detection
  13. Constructing Co-mention Network
  14. Time series processing
  15. Results
  16. ...and 9 more sections

Figures (4)

  • Figure 1: Choosing the best AI model for the trading signal detection task.
  • Figure 2: Exploratory Analysis: (A) User Type Distribution (B) Frequency of Tweets by Major Coin, with Bitcoin as the Most Mentioned (C) Comparison of 9-major coins' mentions in News Outlets versus Influencer Tweets (D) Signal Distribution (E) 'Not Buy' signals predominant for BTC, XRP, and DOT, while 'Buy' Signals are more common for ETH, SOL, ADA, DOGE, SHIB, and BNB.
  • Figure 3: Structure of the cryptocurrencies co-mention network: (A) Influencers mention more coins in their tweets than news outlets do. (B) Tweets signaling a buy mention more coins than tweets not signaling a buy. (C) The co-mention network of top 24 coins. There exists a notable connection between NFT and ETC.
  • Figure 4: Correlation matrix for log returns of prices for pairs of coins in the network holding at least $1\%$ degree share. Upper triangle: Long-term weekly cross-correlation analysis ($k=0$). Lower triangle: Short-term hourly cross-correlation analysis ($k=0$).