Identifying influential factors using machine learning techniques on the intention to receive a COVID-19 booster dose and vaccine fatigue among partially vaccinated individuals

Abstract This study assesses COVID-19 booster intentions and hesitancy in Texas, a state known for its diversity and libertarian values. A survey was conducted with 274 participants residing in Texas between June and July 2022. The analysis examined sociodemographic and health-related factors, trust...

Full description

Saved in:
Bibliographic Details
Main Authors: Athina Bikaki, Justin M. Luningham, Erika L. Thompson, Brittany Krenek, Jamboor K. Vishwanatha, Ioannis A. Kakadiaris
Format: Article
Language:English
Published: Springer 2024-11-01
Series:Discover Public Health
Subjects:
Online Access:https://doi.org/10.1186/s12982-024-00276-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238131727925248
author Athina Bikaki
Justin M. Luningham
Erika L. Thompson
Brittany Krenek
Jamboor K. Vishwanatha
Ioannis A. Kakadiaris
author_facet Athina Bikaki
Justin M. Luningham
Erika L. Thompson
Brittany Krenek
Jamboor K. Vishwanatha
Ioannis A. Kakadiaris
author_sort Athina Bikaki
collection DOAJ
description Abstract This study assesses COVID-19 booster intentions and hesitancy in Texas, a state known for its diversity and libertarian values. A survey was conducted with 274 participants residing in Texas between June and July 2022. The analysis examined sociodemographic and health-related factors, trusted information sources, and preventive behaviors. The survey focused on vaccinated participants and their intention to receive the booster dose, which was categorized into three outcomes: yes, no, and not sure. Machine learning techniques were employed to analyze the survey responses of vaccinated participants to identify the most critical factors. Among the participants, 113 expressed their intention to get the booster (41.2%), 107 did not plan to receive the booster (39.1%), and 54 remained undecided (19.7%). Our findings indicate that the perception of vaccine safety significantly influenced the decision to receive the booster dose. Those who reported trust in social media contacts as reliable information sources were more likely to intend to boost. Additionally, among those hospitalized when diagnosed with COVID-19, the largest proportion were unwilling to receive the booster (47.0%) compared to those who intended to receive the booster (33.3%). In contrast, most of those who believed they would be hospitalized if infected with COVID-19 intended to get the booster. Other factors did not demonstrate a significant association. Our findings are highly transferable and can offer valuable insights, particularly for countries where COVID-19 remains prevalent and are pivotal both presently and in the future for developing strategies to improve booster uptake and shape public health initiatives in epidemic and pandemic outbreaks.
format Article
id doaj-art-3733228c3a7a46a9a223f053e5ba689f
institution Kabale University
issn 3005-0774
language English
publishDate 2024-11-01
publisher Springer
record_format Article
series Discover Public Health
spelling doaj-art-3733228c3a7a46a9a223f053e5ba689f2025-08-20T04:01:43ZengSpringerDiscover Public Health3005-07742024-11-0121111710.1186/s12982-024-00276-wIdentifying influential factors using machine learning techniques on the intention to receive a COVID-19 booster dose and vaccine fatigue among partially vaccinated individualsAthina Bikaki0Justin M. Luningham1Erika L. Thompson2Brittany Krenek3Jamboor K. Vishwanatha4Ioannis A. Kakadiaris5Department of Computer Science, University of HoustonDepartment of Population & Community Health, University of North Texas Health Science CenterDepartment of Quantitative and Qualitative Health Sciences, University of TexasDepartment of Population & Community Health, University of North Texas Health Science CenterInstitute for Health Disparities, University of North Texas Health Science CenterDepartment of Computer Science, University of HoustonAbstract This study assesses COVID-19 booster intentions and hesitancy in Texas, a state known for its diversity and libertarian values. A survey was conducted with 274 participants residing in Texas between June and July 2022. The analysis examined sociodemographic and health-related factors, trusted information sources, and preventive behaviors. The survey focused on vaccinated participants and their intention to receive the booster dose, which was categorized into three outcomes: yes, no, and not sure. Machine learning techniques were employed to analyze the survey responses of vaccinated participants to identify the most critical factors. Among the participants, 113 expressed their intention to get the booster (41.2%), 107 did not plan to receive the booster (39.1%), and 54 remained undecided (19.7%). Our findings indicate that the perception of vaccine safety significantly influenced the decision to receive the booster dose. Those who reported trust in social media contacts as reliable information sources were more likely to intend to boost. Additionally, among those hospitalized when diagnosed with COVID-19, the largest proportion were unwilling to receive the booster (47.0%) compared to those who intended to receive the booster (33.3%). In contrast, most of those who believed they would be hospitalized if infected with COVID-19 intended to get the booster. Other factors did not demonstrate a significant association. Our findings are highly transferable and can offer valuable insights, particularly for countries where COVID-19 remains prevalent and are pivotal both presently and in the future for developing strategies to improve booster uptake and shape public health initiatives in epidemic and pandemic outbreaks.https://doi.org/10.1186/s12982-024-00276-wCOVID-19VaccinationVaccine boosterVaccine hesitancyPandemic fatigueFeature selection
spellingShingle Athina Bikaki
Justin M. Luningham
Erika L. Thompson
Brittany Krenek
Jamboor K. Vishwanatha
Ioannis A. Kakadiaris
Identifying influential factors using machine learning techniques on the intention to receive a COVID-19 booster dose and vaccine fatigue among partially vaccinated individuals
Discover Public Health
COVID-19
Vaccination
Vaccine booster
Vaccine hesitancy
Pandemic fatigue
Feature selection
title Identifying influential factors using machine learning techniques on the intention to receive a COVID-19 booster dose and vaccine fatigue among partially vaccinated individuals
title_full Identifying influential factors using machine learning techniques on the intention to receive a COVID-19 booster dose and vaccine fatigue among partially vaccinated individuals
title_fullStr Identifying influential factors using machine learning techniques on the intention to receive a COVID-19 booster dose and vaccine fatigue among partially vaccinated individuals
title_full_unstemmed Identifying influential factors using machine learning techniques on the intention to receive a COVID-19 booster dose and vaccine fatigue among partially vaccinated individuals
title_short Identifying influential factors using machine learning techniques on the intention to receive a COVID-19 booster dose and vaccine fatigue among partially vaccinated individuals
title_sort identifying influential factors using machine learning techniques on the intention to receive a covid 19 booster dose and vaccine fatigue among partially vaccinated individuals
topic COVID-19
Vaccination
Vaccine booster
Vaccine hesitancy
Pandemic fatigue
Feature selection
url https://doi.org/10.1186/s12982-024-00276-w
work_keys_str_mv AT athinabikaki identifyinginfluentialfactorsusingmachinelearningtechniquesontheintentiontoreceiveacovid19boosterdoseandvaccinefatigueamongpartiallyvaccinatedindividuals
AT justinmluningham identifyinginfluentialfactorsusingmachinelearningtechniquesontheintentiontoreceiveacovid19boosterdoseandvaccinefatigueamongpartiallyvaccinatedindividuals
AT erikalthompson identifyinginfluentialfactorsusingmachinelearningtechniquesontheintentiontoreceiveacovid19boosterdoseandvaccinefatigueamongpartiallyvaccinatedindividuals
AT brittanykrenek identifyinginfluentialfactorsusingmachinelearningtechniquesontheintentiontoreceiveacovid19boosterdoseandvaccinefatigueamongpartiallyvaccinatedindividuals
AT jamboorkvishwanatha identifyinginfluentialfactorsusingmachinelearningtechniquesontheintentiontoreceiveacovid19boosterdoseandvaccinefatigueamongpartiallyvaccinatedindividuals
AT ioannisakakadiaris identifyinginfluentialfactorsusingmachinelearningtechniquesontheintentiontoreceiveacovid19boosterdoseandvaccinefatigueamongpartiallyvaccinatedindividuals