Semi-strong efficient market of Bitcoin and Twitter: An analysis of semantic vector spaces of extracted keywords and light gradient boosting machine models |
| |
| Institution: | 1. College of Finance, Nanjing Agricultural University, Nanjing 210095, China;2. School of Advanced Agricultural Sciences, Peking University, Beijing 100871, China;3. Business School, Hohai University, Nanjing 211100, China;1. University of the Aegean, Department of Business Administration, Greece;2. University of Piraeus, Department of Maritime Studies, 21 Lampraki & Distomou Str., 851833 Piraeus, Greece;1. Center for Quantitative Economics of Jilin University, Changchun 130012, PR China;2. Business and Management School of Jilin University, Changchun 130012, PR China;3. Economics School of Changchun University, Changchun 130021, PR China;1. SKEMA Business School – Université Côte d''Azur, France;2. Rennes School of Business, Rennes, France;3. DCU Business School, Dublin City University, Dublin, Ireland;4. IESEG School of Management, UMR 9221 - LEM - Lille Économie Management, F-59000 Lille, France;5. Univ. Lille, UMR 9221 - LEM - Lille Économie Management, F-59000 Lille, France;6. CNRS, UMR 9221 - LEM - Lille Économie Management, F-59000 Lille, France |
| |
| 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. |
| |
| Keywords: | Efficient-market hypothesis Twitter Bitcoin LightGBM GloVe semantic vector spaces |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
