The Effect of Artificial Intelligence-Assisted Personalized Learning on Student Learning Outcomes: A Meta-Analysis Based on 31 Empirical Research Papers

Abstract

The application of artificial intelligence in education has garnered more attention in academia, and its role in promoting student personalized learning has sparked a lot of discussion. Many researchers have emphasized the positive effect of intelligent technology in supporting student personalized learning; however, there is a lack of systematic data evidence in this regard. This article seeks to evaluate the effects of artificial intelligence-assisted personalized learning on student learning outcomes based on a meta-analysis of 36 experimental and quasi-experimental studies from 31 published papers. The analysis results show that artificial intelligence-assisted personalized learning has moderately positive effects on student learning outcomes in terms of knowledge, competence, and emotional development. Variables such as the type of Edutech applications, learning scenario, and duration of application can moderate the relationship between artificial intelligence-assisted personalized learning and student learning outcomes, whereas the education phase and disciplinary domain do not exhibit significant moderating effects on this relationship. The purpose of this study is to provide implications and references for further research and practical explorations of artificial intelligence application in education.