Paper: arXiv 2508.15825

Authors: Chenghao Liu, Aniket Mahanti, Ranesh Naha, Guanghao Wang, Erwann Sbai

Abstract

As cryptocurrencies gain popularity, the digital asset marketplace becomes increasingly significant. Understanding social media signals offers valuable insights into investor sentiment and market dynamics. Prior research has predominantly focused on text-based platforms such as Twitter. However, video content remains underexplored, despite potentially containing richer emotional and contextual sentiment that is not fully captured by text alone. In this study, we present a multimodal analysis comparing TikTok and Twitter sentiment, using large language models to extract insights from both video and text data. We investigate the dynamic dependencies and spillover effects between social media sentiment and cryptocurrency market indicators. Our results reveal that TikTok’s video-based sentiment significantly influences speculative assets and short-term market trends, while Twitter’s text-based sentiment aligns more closely with long-term dynamics. Notably, the integration of cross-platform sentiment signals improves forecasting accuracy by up to 20%.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 7.5/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper employs statistical methods like spillover analysis and regression models with LLMs for sentiment extraction, but lacks deep mathematical derivations or novel theoretical frameworks. Empirically, it is strong with a defined methodology, specific dataset (TikTok/Twitter), and quantitative results (20% accuracy improvement, 35% Dogecoin prediction gain), indicating backtest-ready implementation.

Research Flowchart

  flowchart TD
  Goal["Research Goal:<br/>Analyze TikTok & Twitter sentiment<br/>impact on crypto market dynamics?"]
  Data["Data Inputs:<br/>TikTok (Video) & Twitter (Text)<br/>+ Crypto Market Indicators"]
  Method["Methodology:<br/>Multimodal Analysis with Large Language Models<br/>(Video & Text Feature Extraction)"]
  Process["Computation:<br/>Analyze Sentiment Spillover &<br/>Dynamic Dependencies between Platforms & Market"]
  Findings["Key Outcomes:<br/>1. TikTok sentiment drives short-term trends<br/>2. Twitter sentiment aligns with long-term trends<br/>3. Cross-platform integration improves accuracy by 20%"]
  
  Goal --> Data
  Data --> Method
  Method --> Process
  Process --> Findings