The impact of student number and class duration on the effectiveness of artificial intelligence-assisted learning

Abstract

The aim of this study is to determine the effects of class size and course duration on students’ academic performance in artificial intelligence
(AI)-supported learning environments and to develop recommendations for optimizing these parameters. Previous research has not examined the simultaneous impact of class size and course duration on the effectiveness of AI-assisted learning. To achieve this objective, a quasi-experimental design was employed, including a control group (CG) (n=75) and an experimental group (EG) (n=20). Outcomes were assessed using pre-test and post-test measures evaluating knowledge of Chinese history. Statistical hypotheses were tested using independent samples t-tests and one-way analysis of variance (ANOVA). The EG demonstrated a significantly higher mean post-test score (85.6) compared to the CG (76.3), with statistical significance at p<0.05. The effect size (Cohen’s d) was approximately 1.65, indicating a high level of practical significance. The findings provide a foundation for developing targeted strategies to integrate AI into higher education.