Enhancing Health Education Through AI-enabled Game
Deep Blue (University of Michigan) · 01.11.2024
DOI: 10.7302/24871 ↗Kurz gefasst
Fachartikel in der Zeitschrift Deep Blue (University of Michigan), erschienen am 01.11.2024. Verfasst von Chin und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Background
Mobile app-based games have emerged as promising tools for engaging children in health education, particularly in resource-constrained settings. Fooya! is a clinically proven mobile application designed to promote healthy habits among children through engaging gameplay. While previous studies have demonstrated its effectiveness in improving nutritional choices, the specific gameplay patterns that most effectively enhance knowledge of infectious disease prevention remain unexplored.
Objectives
This study aims to: 1. Identify specific gameplay patterns within Fooya! that are associated with higher infectious disease prevention knowledge among children. 2. Understand how these patterns can inform personalized game design and contribute to generalizable learning theories.
Methods
We conducted an 11-week longitudinal two-arm cluster randomized controlled trial with 240 school children in Grades 1-8 at a government school in Chennai, India, between July and September 2022. Grades were paired (1-2, 3-4, 5-6, 7-8) and randomly assigned to either the treatment group, which played Fooya! for 30 minutes weekly, or the control group, which played non-health educational games for the same duration. Data collected included telemetry gameplay data, assessment data such as pre- and post-intervention knowledge tests focusing on infectious disease prevention, and additional data such as demographics, actual food choices, and parental surveys. Sequence analysis and group-based trajectory modeling are being employed to identify gameplay patterns and examine their association with knowledge outcomes. Unsupervised learning algorithms such as k-means clustering are used to group similar gameplay behaviors. Ethical approvals were obtained, informed consent was secured from parents/guardians, and data privacy measures were strictly enforced.
Results
As this research is a work in progress, definitive results are not yet available. Preliminary analysis using time series clustering has been performed, indicating potential patterns in gameplay behavior that may correlate with learning outcomes. These initial findings suggest variations in how different gameplay sequences might influence knowledge acquisition. Further analysis is ongoing to validate these observations and to explore the relationships between specific gameplay patterns and improvements in infectious disease prevention knowledge.
Conclusions
While conclusive results are pending, the preliminary findings underscore the potential of identifying effective gameplay patterns to enhance health education among children. Understanding these patterns could provide valuable insights into optimizing mobile health games like Fooya! for better educational outcomes. The study aims to support the development of personalized game-based learning strategies and contribute to generalizable theories of learning in digital environments. Future work will focus on completing the data analysis, interpreting the results within relevant educational theories, and assessing the implications for game design and health education practices.
Schlagwörter
Zitieren
APA
Chin, J.H., & Ladhania, R. (2024). Enhancing Health Education Through AI-enabled Game. Deep Blue (University of Michigan). https://doi.org/10.7302/24871
Vancouver
Chin, J.H., Ladhania R. Enhancing Health Education Through AI-enabled Game. Deep Blue (University of Michigan). 2024. doi:10.7302/24871
BibTeX
@article{Chin2024,
author = {Chin and J.H. and Ladhania, Rahul},
title = {Enhancing Health Education Through AI-enabled Game},
journal = {Deep Blue (University of Michigan)},
year = {2024},
doi = {10.7302/24871}
}
EUVIMED