Gender preferences in cryptocurrency systems: Sentiment analysis and predictive modelling

Samer Muthana Sarsam; Ahmed Ibrahim Alzahrani; Hosam Al-Samarraie; Fahad  Alblehai

doi:10.1080/10293523.2024.2410059

Gender preferences in cryptocurrency systems: Sentiment analysis and predictive modelling

Samer Muthana Sarsam, Ahmed Ibrahim Alzahrani, Hosam Al-Samarraie, Fahad Alblehai

CBL School of Management

Research output: Contribution to journal › Article › peer-review

6 Downloads (Pure)

Abstract

This study explored the role of gender preferences in cryptocurrency investments using sentiment analysis. X (Twitter) users’ gender (male/female) together with relevant sentiments (positive/negative) were extracted and investigated in this study. The Latent Dirichlet Allocation technique was utilised to model gender-related topics in an attempt to understand male and female users’ preferences to invest in cryptocurrency. The Apriori algorithm was employed to predict the highly associated investment terminologies with each gender. A predictive model was built to predict the type of digital currency preferred by X users. Using sentiment-based gender data, the results showed a high prediction accuracy (98.64%) of digital currency preferences. The study demonstrated that male users were most likely to use Bitcoin, compared to female users who preferred Ethereum. This study further offers a novel mechanism to predict users’ preferences for cryptocurrency platforms using their sentiment features. It extends the knowledge of cryptocurrencies in the financial business profile by revealing how investors’ gender contributes to investment-related decisions.

Original language	English
Pages (from-to)	(In-Press)
Number of pages	15
Journal	Investment Analysts Journal
Volume	(In-Press)
Early online date	22 Nov 2024
DOIs	https://doi.org/10.1080/10293523.2024.2410059
Publication status	E-pub ahead of print - 22 Nov 2024

Bibliographical note

This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives License (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited, and is not altered, transformed, or built upon in any way. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) or with their consent.

Funding

This work is funded by the Researchers Supporting Project number (RSP 2024/157), King Saud University, Riyadh, Saudi Arabia.

Funders	Funder number
King Saud University	RSP 2024/157

Keywords

Cryptocurrency
Gender
Bitcoin
Ethereum
X (Twitter)
Sentiment Analysis

Access to Document

10.1080/10293523.2024.2410059Licence: CC BY-NC-ND

Sarsam2024VoRFinal published version, 1.64 MBLicence: CC BY-NC-ND

Cite this

@article{04b6862952a34d65ab883d8dd7985885,

title = "Gender preferences in cryptocurrency systems: Sentiment analysis and predictive modelling",

abstract = "This study explored the role of gender preferences in cryptocurrency investments using sentiment analysis. X (Twitter) users{\textquoteright} gender (male/female) together with relevant sentiments (positive/negative) were extracted and investigated in this study. The Latent Dirichlet Allocation technique was utilised to model gender-related topics in an attempt to understand male and female users{\textquoteright} preferences to invest in cryptocurrency. The Apriori algorithm was employed to predict the highly associated investment terminologies with each gender. A predictive model was built to predict the type of digital currency preferred by X users. Using sentiment-based gender data, the results showed a high prediction accuracy (98.64%) of digital currency preferences. The study demonstrated that male users were most likely to use Bitcoin, compared to female users who preferred Ethereum. This study further offers a novel mechanism to predict users{\textquoteright} preferences for cryptocurrency platforms using their sentiment features. It extends the knowledge of cryptocurrencies in the financial business profile by revealing how investors{\textquoteright} gender contributes to investment-related decisions.",

keywords = "Cryptocurrency, Gender, Bitcoin, Ethereum, X (Twitter), Sentiment Analysis",

author = "Sarsam, {Samer Muthana} and Alzahrani, {Ahmed Ibrahim} and Hosam Al-Samarraie and Fahad Alblehai",

note = "This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives License (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited, and is not altered, transformed, or built upon in any way. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) or with their consent.",

year = "2024",

month = nov,

day = "22",

doi = "10.1080/10293523.2024.2410059",

language = "English",

volume = "(In-Press)",

pages = "(In--Press)",

journal = "Investment Analysts Journal",

issn = "1029-3523",

publisher = "Taylor and Francis Group",

}

TY - JOUR

T1 - Gender preferences in cryptocurrency systems

T2 - Sentiment analysis and predictive modelling

AU - Sarsam, Samer Muthana

AU - Alzahrani, Ahmed Ibrahim

AU - Al-Samarraie, Hosam

AU - Alblehai, Fahad

N1 - This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives License (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited, and is not altered, transformed, or built upon in any way. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) or with their consent.

PY - 2024/11/22

Y1 - 2024/11/22

N2 - This study explored the role of gender preferences in cryptocurrency investments using sentiment analysis. X (Twitter) users’ gender (male/female) together with relevant sentiments (positive/negative) were extracted and investigated in this study. The Latent Dirichlet Allocation technique was utilised to model gender-related topics in an attempt to understand male and female users’ preferences to invest in cryptocurrency. The Apriori algorithm was employed to predict the highly associated investment terminologies with each gender. A predictive model was built to predict the type of digital currency preferred by X users. Using sentiment-based gender data, the results showed a high prediction accuracy (98.64%) of digital currency preferences. The study demonstrated that male users were most likely to use Bitcoin, compared to female users who preferred Ethereum. This study further offers a novel mechanism to predict users’ preferences for cryptocurrency platforms using their sentiment features. It extends the knowledge of cryptocurrencies in the financial business profile by revealing how investors’ gender contributes to investment-related decisions.

AB - This study explored the role of gender preferences in cryptocurrency investments using sentiment analysis. X (Twitter) users’ gender (male/female) together with relevant sentiments (positive/negative) were extracted and investigated in this study. The Latent Dirichlet Allocation technique was utilised to model gender-related topics in an attempt to understand male and female users’ preferences to invest in cryptocurrency. The Apriori algorithm was employed to predict the highly associated investment terminologies with each gender. A predictive model was built to predict the type of digital currency preferred by X users. Using sentiment-based gender data, the results showed a high prediction accuracy (98.64%) of digital currency preferences. The study demonstrated that male users were most likely to use Bitcoin, compared to female users who preferred Ethereum. This study further offers a novel mechanism to predict users’ preferences for cryptocurrency platforms using their sentiment features. It extends the knowledge of cryptocurrencies in the financial business profile by revealing how investors’ gender contributes to investment-related decisions.

KW - Cryptocurrency

KW - Gender

KW - Bitcoin

KW - Ethereum

KW - X (Twitter)

KW - Sentiment Analysis

U2 - 10.1080/10293523.2024.2410059

DO - 10.1080/10293523.2024.2410059

M3 - Article

SN - 1029-3523

VL - (In-Press)

SP - (In-Press)

JO - Investment Analysts Journal

JF - Investment Analysts Journal

ER -

Gender preferences in cryptocurrency systems: Sentiment analysis and predictive modelling

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Fingerprint

Cite this