Deep Learning-Based Cryptocurrency Sentiment Construction

20 Pages Posted: 8 Jan 2019

See all articles by Sergey Nasekin

Sergey Nasekin

Humboldt University of Berlin - Center for Applied Statistics and Economics (CASE)

Cathy Yi‐Hsuan Chen

Humboldt Universität zu Berlin

Date Written: December 10, 2018

Abstract

We study investor sentiment on a non-classical asset, cryptocurrencies using a “crypto-specific lexicon” recently proposed in Chen et al. (2018) and statistical learning methods. We account for context-specific information and word similarity by learning word embeddings via neural network-based Word2Vec model. On top of pre-trained word vectors, we apply popular machine learning methods such as recursive neural networks for sentence-level classification and sentiment index construction. We perform this analysis 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. The constructed sentiment indices are value-relevant in terms of its return and volatility predictability for the cryptocurrency market index.

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

JEL Classification: G41, G4, G12

Suggested Citation

Nasekin, Sergey and Chen, Cathy Yi‐Hsuan, Deep Learning-Based Cryptocurrency Sentiment Construction (December 10, 2018). Available at SSRN: https://ssrn.com/abstract=3310784 or http://dx.doi.org/10.2139/ssrn.3310784

Sergey Nasekin

Humboldt University of Berlin - Center for Applied Statistics and Economics (CASE) ( email )

Spandauer Strasse 1
Berlin, D-10178
Germany

Cathy Yi‐Hsuan Chen (Contact Author)

Humboldt Universität zu Berlin ( email )

Unter den Linden 6,
Berlin, 10099
Germany
493020935625 (Phone)

HOME PAGE: http://https://www.wiwi.hu-berlin.de/de/professuren/vwl/statistik/members/personalpages/chencath

Register to save articles to
your library

Register

Paper statistics

Downloads
169
rank
172,710
Abstract Views
728
PlumX Metrics