A Scoping Review of Machine Learning Applications in Education Research (Poster 27)

• In Event: AERA Poster Session Thursday 8:00 a.m.
  In Poster Session: Advancements in Educational Data Analysis: Machine Learning, Multilevel Models, and Beyond

Abstract

This methodological scoping review investigates the application of machine learning (ML) for data analysis in educational research from 2000 to 2024. By examining 8,396 articles from top-tier education journals, we explore trends, methodological choices, and educational outcomes and data types most commonly associated with ML applications. Our preliminary findings indicate a significant increase in ML-based publications since 2021, with educational technology and learning sciences being the most prominent subfields. Supervised learning and text mining are the most commonly employed techniques. Additionally, post-secondary education settings and behavioral measures dominate the research focus. This review highlights the growing influence of ML in education, underscoring the need for methodological advancements and anticipating broader adoption across diverse educational levels.

Authors

• Michael Broda, Virginia Commonwealth University

• Tzu-Wei Wang, Virginia Commonwealth University

• Jeen Mariam Joy, Virginia Commonwealth University

• John Hui, Virginia Commonwealth University

• Chi-Ning Chang, Virginia Commonwealth University

• Moe Debbagh Greene, Virginia Commonwealth University

• Chin-Chih Chen, Virginia Commonwealth University

• Amy Corning, Virginia Commonwealth University

• Yuyan Xia, University of Kentucky

• Xun Liu, Virginia Commonwealth University