Deep learning-based cryptocurrency sentiment construction

Arbeitspapier

We study investor sentiment on a non-classical asset, cryptocurrencies using a “cryptospecificlexicon” recently proposed in Chen et al. (2018) and statistical learning methods.We account for context-specific information and word similarity by learning word embeddingsvia neural network-based Word2Vec model. On top of pre-trained word vectors, weapply popular machine learning methods such as recursive neural networks for sentencelevelclassification and sentiment index construction. We perform this analysis on a noveldataset of 1220K messages related to 425 cryptocurrencies posted on a microblogging platformStockTwits during the period between March 2013 and May 2018. The constructed sentiment indices are value-relevant in terms of its return and volatility predictability for thecryptocurrency market index.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: IRTG 1792 Discussion Paper ; No. 2018-066

Classification and Topics

• Classification: Wirtschaft ; Behavioral Finance: Role and Effects of Psychological, Emotional, Social, and Cognitive Factors on Decision Making in Financial Markets‡ ; Asset Pricing; Trading Volume; Bond Interest Rates
• Subject: sentiment analysis ; lexicon ; social media ; word embedding ; deep learning

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Nasekin, Sergey ; Chen, Cathy Yi-Hsuan
• Event: Veröffentlichung
• (who): Humboldt-Universität zu Berlin, International Research Training Group 1792 "High Dimensional Nonstationary Time Series"
• (where): Berlin
• (when): 2018

Further information

• Handle: http://hdl.handle.net/10419/230776
• Last update: 10.03.2025, 11:42 AM CET