On the predictive power of tweet sentiments and attention on bitcoin

Suardi, S; Rasel, AR; Liu, B

On the predictive power of tweet sentiments and attention on bitcoin

Suardi, S Rasel, AR Liu, B

Permalink

Publisher:: Elsevier BV
Publication Type:: Journal Article
Citation:: International Review of Economics and Finance, 2022, 79, pp. 289-301
Issue Date:: 2022-05-01

Closed Access

	Filename	Description	Size
	10.1016 j.iref.2022.02.017.pdf	Published version	670.96 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Suardi, S
dc.contributor.author	Rasel, AR
dc.contributor.author	Liu, B
dc.date.accessioned	2022-09-16T04:22:52Z
dc.date.available	2022-09-16T04:22:52Z
dc.date.issued	2022-05-01
dc.identifier.citation	International Review of Economics and Finance, 2022, 79, pp. 289-301
dc.identifier.issn	1059-0560
dc.identifier.uri	http://hdl.handle.net/10453/161851
dc.description.abstract	This paper investigates the predictive power of information contained in social media tweets on bitcoin market dynamics. Using Valence Aware Dictionary for Sentiment Reasoning (VADER), we extract useful information from tweets and construct two factors – sentiment dispersion (SD) and investor attention (IA) – to test their predictive power. We show that investors face greater return volatility for rising sentiment dispersion associated with more significant market uncertainty. Further, IA is found to predict bitcoin trading volume but not returns and volatility. Finally, we design an IA-induced trading strategy that yields superior performance to the passive buy-and-hold strategy in 2018. However, it does not deliver superior performance in other years during the sample period suggesting that investor attention alone as a trading parameter does not produce superior performance over the long term.
dc.language	en
dc.publisher	Elsevier BV
dc.relation.ispartof	International Review of Economics and Finance
dc.relation.isbasedon	10.1016/j.iref.2022.02.017
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	1401 Economic Theory, 1402 Applied Economics, 1502 Banking, Finance and Investment
dc.subject.classification	Economics
dc.title	On the predictive power of tweet sentiments and attention on bitcoin
dc.type	Journal Article
utslib.citation.volume	79
utslib.for	1401 Economic Theory
utslib.for	1402 Applied Economics
utslib.for	1502 Banking, Finance and Investment
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Business
pubs.organisational-group	/University of Technology Sydney/Faculty of Business/Finance Discipline
utslib.copyright.status	closed_access	*
dc.date.updated	2022-09-16T04:22:51Z
pubs.publication-status	Published
pubs.volume	79

Abstract:

This paper investigates the predictive power of information contained in social media tweets on bitcoin market dynamics. Using Valence Aware Dictionary for Sentiment Reasoning (VADER), we extract useful information from tweets and construct two factors – sentiment dispersion (SD) and investor attention (IA) – to test their predictive power. We show that investors face greater return volatility for rising sentiment dispersion associated with more significant market uncertainty. Further, IA is found to predict bitcoin trading volume but not returns and volatility. Finally, we design an IA-induced trading strategy that yields superior performance to the passive buy-and-hold strategy in 2018. However, it does not deliver superior performance in other years during the sample period suggesting that investor attention alone as a trading parameter does not produce superior performance over the long term.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/161851