Financial Twitter Sentiment on Bitcoin Return and High-Frequency Volatility
This paper studies how sentiment affect Bitcoin pricingby examining, at an hourly frequency,the linkagebetween sentiment of finance-related Twitter messages and return as well asthe volatilityof Bitcoin as a financial asset. On the one hand, there was calculatedthe return from minute-level Bitcoin e...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Institute for International Cooperation Development
2021-01-01
|
Series: | Virtual Economics |
Subjects: | |
Online Access: | https://virtual-economics.eu/index.php/VE/article/view/101/73 |
id |
doaj-8103c122807d43f5974f43d4be6a453d |
---|---|
record_format |
Article |
spelling |
doaj-8103c122807d43f5974f43d4be6a453d2021-07-22T19:40:06ZengInstitute for International Cooperation DevelopmentVirtual Economics2657-40472021-01-014171810.34021/ve.2021.04.01(1)Financial Twitter Sentiment on Bitcoin Return and High-Frequency VolatilityXiang Gao0https://orcid.org/0000-0003-4914-557XWeige Huang1https://orcid.org/0000-0002-0615-3302Hua Wang2https://orcid.org/0000-0001-5186-4165Shanghai Business School, Shanghai, ChinaZhongnan University of Economics and Law, Wuhan, ChinaShenzhen Technology University, Shenzhen, ChinaThis paper studies how sentiment affect Bitcoin pricingby examining, at an hourly frequency,the linkagebetween sentiment of finance-related Twitter messages and return as well asthe volatilityof Bitcoin as a financial asset. On the one hand, there was calculatedthe return from minute-level Bitcoin exchange quotes and use of both rolling variance and high-minus-low price to proxy for Bitcoin volatility per each trading hour. On the other hand, the moodsignals from tweets were extracted based on a list of positive, negative, and uncertain words according to the Loughran-McDonald finance-specific dictionary. These signals were translated by categorizing each tweetinto one of three sentiments, namely, bullish, bearish,and null. Then the total number of tweets were adoptedin each category over one hour and their differences as potential Bitcoin price predictors. The empiricalresults indicate thatafter controlling a list of lagged returns and volatilities,stronger bullish sentimentsignificantly foreshadows higher Bitcoin return and volatilityover the time range of 24 hours. While bearish and neutral financial Twitter sentiments have no such consistent performance, the difference between bullish and bearish ratings can improve prediction consistency. Overall, this research results add to the growing Bitcoin literature by demonstrating that the Bitcoin pricing mechanismcan be partially revealedby themomentum on sentiment in social media networks, justifying a sentimental appetitefor cryptocurrency investment.https://virtual-economics.eu/index.php/VE/article/view/101/73bitcoincryptocurrencysentimenttwittersocial mediavolatility |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiang Gao Weige Huang Hua Wang |
spellingShingle |
Xiang Gao Weige Huang Hua Wang Financial Twitter Sentiment on Bitcoin Return and High-Frequency Volatility Virtual Economics bitcoin cryptocurrency sentiment social media volatility |
author_facet |
Xiang Gao Weige Huang Hua Wang |
author_sort |
Xiang Gao |
title |
Financial Twitter Sentiment on Bitcoin Return and High-Frequency Volatility |
title_short |
Financial Twitter Sentiment on Bitcoin Return and High-Frequency Volatility |
title_full |
Financial Twitter Sentiment on Bitcoin Return and High-Frequency Volatility |
title_fullStr |
Financial Twitter Sentiment on Bitcoin Return and High-Frequency Volatility |
title_full_unstemmed |
Financial Twitter Sentiment on Bitcoin Return and High-Frequency Volatility |
title_sort |
financial twitter sentiment on bitcoin return and high-frequency volatility |
publisher |
Institute for International Cooperation Development |
series |
Virtual Economics |
issn |
2657-4047 |
publishDate |
2021-01-01 |
description |
This paper studies how sentiment affect Bitcoin pricingby examining, at an hourly frequency,the linkagebetween sentiment of finance-related Twitter messages and return as well asthe volatilityof Bitcoin as a financial asset. On the one hand, there was calculatedthe return from minute-level Bitcoin exchange quotes and use of both rolling variance and high-minus-low price to proxy for Bitcoin volatility per each trading hour. On the other hand, the moodsignals from tweets were extracted based on a list of positive, negative, and uncertain words according to the Loughran-McDonald finance-specific dictionary. These signals were translated by categorizing each tweetinto one of three sentiments, namely, bullish, bearish,and null. Then the total number of tweets were adoptedin each category over one hour and their differences as potential Bitcoin price predictors. The empiricalresults indicate thatafter controlling a list of lagged returns and volatilities,stronger bullish sentimentsignificantly foreshadows higher Bitcoin return and volatilityover the time range of 24 hours. While bearish and neutral financial Twitter sentiments have no such consistent performance, the difference between bullish and bearish ratings can improve prediction consistency. Overall, this research results add to the growing Bitcoin literature by demonstrating that the Bitcoin pricing mechanismcan be partially revealedby themomentum on sentiment in social media networks, justifying a sentimental appetitefor cryptocurrency investment. |
topic |
bitcoin cryptocurrency sentiment social media volatility |
url |
https://virtual-economics.eu/index.php/VE/article/view/101/73 |
work_keys_str_mv |
AT xianggao financialtwittersentimentonbitcoinreturnandhighfrequencyvolatility AT weigehuang financialtwittersentimentonbitcoinreturnandhighfrequencyvolatility AT huawang financialtwittersentimentonbitcoinreturnandhighfrequencyvolatility |
_version_ |
1721291107685367808 |