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

Svetlana Vladimirovna Dmitrichenkova, Elena Anatolyevna Dolzhich, Ainash Alzhanova, Iza A. Berechikidze

2026

Data confidence 70 medium

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

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.