Decoding Market Emotions in Cryptocurrency Tweets via Predictive Statement Classification with Machine Learning and Transformers

2026-03-25

AI Summary

This study addresses the challenge of identifying market-predictive statements in cryptocurrency-related tweets and analyzing their implicit sentiment. To this end, the authors propose a two-stage classification framework: the first stage distinguishes predictive from non-predictive tweets, while the second categorizes predictive tweets into bullish, bearish, or neutral classes. A balanced dataset is constructed by combining human-annotated data with synthetic examples generated by GPT, and sentiment features are extracted using SenticNet. Experimental results show that Transformer-based models achieve the highest F1 score in the first stage, whereas traditional machine learning methods perform best in the second stage. Data augmentation with GPT effectively mitigates class imbalance and enhances overall performance, further revealing significant associations between prediction categories and sentiment features.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Machine Learning: Feature Construction/Reformulation
• Data Mining & Knowledge Management: Semantic Web

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The growing prominence of cryptocurrencies has triggered widespread public engagement and increased speculative activity, particularly on social media platforms. This study introduces a novel classification framework for identifying predictive statements in cryptocurrency-related tweets, focusing on five popular cryptocurrencies: Cardano, Matic, Binance, Ripple, and Fantom. The classification process is divided into two stages: Task 1 involves binary classification to distinguish between Predictive and Non-Predictive statements. Tweets identified as Predictive proceed to Task 2, where they are further categorized as Incremental, Decremental, or Neutral. To build a robust dataset, we combined manual and GPT-based annotation methods and utilized SenticNet to extract emotion features corresponding to each prediction category. To address class imbalance, GPT-generated paraphrasing was employed for data augmentation. We evaluated a wide range of machine learning, deep learning, and transformer-based models across both tasks. The results show that GPT-based balancing significantly enhanced model performance, with transformer models achieving the highest F1-score in Task 1, while traditional machine learning models performed best in Task 2. Furthermore, our emotion analysis revealed distinct emotional patterns associated with each prediction category across the different cryptocurrencies.

Problem

• cryptocurrency
• predictive statement classification
• market emotion
• social media
• tweet analysis

Innovation

• predictive statement classification
• cryptocurrency sentiment analysis
• GPT-based data augmentation
• two-stage classification framework
• emotion-aware machine learning