International Journal of
Information and Education Technology

Abstract

This meta-analysis examines the effectiveness of chatbot integration in science education by synthesizing quantitative findings from selected peer-reviewed studies. Employing a rigorous meta-analytic approach, eight studies published between 2007 and 2024 were analyzed using a random-effects model. The inclusion criteria focused on quasi-experimental research measuring student performance in science subjects. Effect sizes were calculated using Hedges’ g, with additional analyses conducted to assess heterogeneity, publication bias, and subgroup differences. Findings indicate that chatbot-assisted instruction significantly improves student performance compared to traditional methods. AI-driven chatbots showed notably higher effectiveness than rule-based systems, highlighting the value of adaptive, interactive technologies in educational contexts. Despite high variability among studies, sensitivity analyses confirmed the stability of the results. The findings suggest that chatbot integration—particularly when designed for dynamic, personalized learning—can meaningfully enhance science education outcomes. These insights offer practical implications for educators and policymakers aiming to implement AI tools in curriculum design.