Deep Learning-Based Cryptocurrency Sentiment Construction

Abstract

We study investor sentiment on a non-classical asset such as cryptocurrency using machine learning methods. We account for context-specific information and word similarity by using efficient language modelling tools such as construction of featurized word representations (embeddings) and recursive neural networks (RNNs). We apply these tools for sentence-level sentiment classification and sentiment index construction. This analysis is performed on a novel dataset of 1220K messages related to 425 cryptocurrencies posted on a microblogging platform StockTwits during the period between March 2013 and May 2018. Both in- and out-of-sample predictive regressions are run to test significance of the constructed sentiment index variables. We find that the constructed sentiment indices are informative regarding returns' and volatility predictability of the cryptocurrency market index.

Keywords: sentiment analysis, lexicon, social media, word embedding, deep learning, LSTM

JEL Classification: G41, G4, G12