본문 바로가기
  • Home

Design and Evaluation of a Satisfaction Prediction Model for the Digital Saessak Playground Program for Elementary School Students

  • Journal of Internet of Things and Convergence
  • Abbr : JKIOTS
  • 2026, 12(1), pp.157~164
  • Publisher : The Korea Internet of Things Society
  • Research Area : Engineering > Computer Science > Internet Information Processing
  • Received : October 12, 2025
  • Accepted : January 19, 2026
  • Published : February 28, 2026

Keun-Ho Lee 1

1백석대학교

Accredited

ABSTRACT

The Digital Saessak Playground Program is an experiential education initiative designed to enhance digital competencies and learning engagement among elementary school students. However, previous satisfaction surveys have been mainly used for simple statistical reporting, which limits their practical use for program improvement and decision-making. The purpose of this study is to analyze student satisfaction with the Digital Saessak Playground Program and to design a machine learning– based prediction model. To achieve this, satisfaction survey data were refined into a low-data dataset suitable for regression-based machine learning experiments. Linear Regression, Random Forest, and K-Nearest Neighbors models were implemented and compared in the experimental analysis. The results indicate that the Random Forest model outperformed the other models in terms of prediction accuracy. Furthermore, feature importance analysis revealed that instructor feedback and content quality are the most influential factors affecting overall student satisfaction. These findings suggest that the proposed approach can support data-driven improvements and evidence-based policy development in elementary digital education programs.

Citation status

* References for papers published after 2024 are currently being built.