Semi-strong Efficient Market of Bitcoin and Twitter: an Analysis of Semantic Vector Spaces of Extracted Keywords and Light Gradient Boosting Machine Models

TL;DR

This paper investigates Bitcoin market efficiency during 2017-2022 by analyzing a large dataset of tweets and applying semantic vector space analysis and Light Gradient Boosting Machine models to predict market movements.

Contribution

It introduces a novel approach using fundamental keyword extraction and semantic vector analysis, moving beyond sentiment analysis to assess market efficiency.

Findings

High accuracy in predicting market movements from tweet data

Market reactions are faster and more precise than previously thought

Semantic analysis of keywords effectively captures market signals

Abstract

This study extends the examination of the Efficient-Market Hypothesis in Bitcoin market during a five year fluctuation period, from September 1 2017 to September 1 2022, by analyzing 28,739,514 qualified tweets containing the targeted topic "Bitcoin". Unlike previous studies, we extracted fundamental keywords as an informative proxy for carrying out the study of the EMH in the Bitcoin market rather than focusing on sentiment analysis, information volume, or price data. We tested market efficiency in hourly, 4-hourly, and daily time periods to understand the speed and accuracy of market reactions towards the information within different thresholds. A sequence of machine learning methods and textual analyses were used, including measurements of distances of semantic vector spaces of information, keywords extraction and encoding model, and Light Gradient Boosting Machine (LGBM) classifiers. Our results suggest that 78.06% (83.08%), 84.63% (87.77%), and 94.03% (94.60%) of hourly, 4-hourly, and daily bullish (bearish) market movements can be attributed to public information within organic tweets.