Exploring Factors Affecting Computational Thinking through Machine Learning and Multilevel Modeling Methods

• In Event: Computational Thinking and Cognitive Skill Development

Abstract

This study explores factors affecting eighth-grade students’ computational thinking (CT) skills using data from the 2018 U.S. sample of the International Computer and Information Literacy Study. Key predictors were identified using machine learning, including students’ information and communication technology (ICT) learning experiences, ICT self-efficacy, socioeconomic status, and school characteristics. These associations were subsequently tested using multilevel modeling analysis. Results showed that most ICT experiences positively predicted CT skills, while the use of specialist applications was negatively associated. These findings enhance understanding of CT development and the role of ICT in education. The integrated methodological approach provides nuanced insights into fostering students’ CT skills and highlights the importance of data-driven approach for future research.

Authors

• Tzu-Wei Wang, Virginia Commonwealth University

• Michael Broda, Virginia Commonwealth University

• Christine Lee Bae, Virginia Commonwealth University

• Monty Jones, Virginia Commonwealth University