2021
DOI: 10.1108/imds-04-2021-0232
| View full text |Cite
|
Sign up to set email alerts
|

Abstract: PurposeThe authors examine cryptocurrency market behavior using a hidden Markov model (HMM). Under the assumption that the cryptocurrency market has unobserved heterogeneity, an HMM allows us to study (1) the extent to which cryptocurrency markets shift due to interactions with social sentiment during a bull or bear market and (2) the heterogeneous pattern of cryptocurrency market behavior under these two market conditions.Design/methodology/approachThe authors advance the HMM model based on two six-month data… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
3
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
3
2
2

Relationship

0
7

Authors

Journals

citations
Cited by 8 publications
(4 citation statements)
references
References 98 publications
1
3
0
Order By: Relevance
“…In particular, possibly due to human psychology, both inference and diagnosis analyses show more significant changes in the number of tweets in the occurrence of an upward trend market. This result is in line with other studies such as (Kim et al, 2021) where an upward trend market is highlighted as more influential in comparison to a downward trend market in investigating the social sentiments of people's tweets. The fluctuation in the number of tweets is observed more in Binance…”
Section: Inferencesupporting
confidence: 92%
See 1 more Smart Citation
“…In particular, possibly due to human psychology, both inference and diagnosis analyses show more significant changes in the number of tweets in the occurrence of an upward trend market. This result is in line with other studies such as (Kim et al, 2021) where an upward trend market is highlighted as more influential in comparison to a downward trend market in investigating the social sentiments of people's tweets. The fluctuation in the number of tweets is observed more in Binance…”
Section: Inferencesupporting
confidence: 92%
“…In a similar study, Rouhani & Abedin (2019) show that Ripple has the highest percentage of positive tweets (52%), and Bitcoin receives the highest percentage of negative tweets (27%) among all the cryptocurrencies by analysing around five million tweets. The predictive power of social media sentiment analysis is studied in Kraaijeveld & De Smedt (2020) and Kim et al (2021), and it is shown that Twitter sentiment has predictive power for price returns of Bitcoin, Bitcoin Cash, and Litecoin, and cryptocurrency markets are more responsive to positive social sentiment when it is in a downward trend.…”
Section: Related Literaturementioning
confidence: 99%
“…2) Transition matrix P : We model the evolution of the total computing power in the blockchain as a time-homogeneous Markov chain with transition matrix P . This Markov assumption is widely used [14]. We will justify the Markov assumption in Sec.IV using a real Bitcoin dataset.…”
Section: A Pomdp Model For the Energy-efficient Mining Problem In Blo...mentioning
confidence: 99%
“…Related to the modeling of the blockchain system, [12] and [13] employ a Markov process model to study performance and network security in a distributed ledger. The evolution of cryptocurrency as a Hidden Markov Model is explored in [12], [14].…”
Section: Related Workmentioning
confidence: 99%