Authors: Dr Abhijit Das, Dr Namrata Yadav Das
Abstract: Background: Artificial intelligence (AI) technologies are increasingly integrated into educational settings to enhance student engagement and classroom interaction. However, the evidence base regarding their effectiveness remains fragmented. This systematic review synthesizes empirical evidence on the role of AI in improving student engagement and classroom interaction in K-12 and higher education contexts. Methods: Following PRISMA 2020 guidelines, we conducted a comprehensive literature search across multiple databases (SciSpace, Google Scholar, PubMed) from January 2016 to March 2026. Studies were included if they reported empirical evidence on AI interventions targeting student engagement or classroom interaction outcomes in educational settings. Two independent reviewers screened 267 unique records, assessed 204 full-text articles, and included 142 studies in the final synthesis. Risk of bias was assessed using the ROBINS-I tool for six representative studies. Results: From 267 unique records identified, 142 studies met inclusion criteria after title/abstract screening and full-text assessment. Six representative studies (N=50–20,000+ participants) demonstrated that AI interventions—including personalized recommendation systems, intelligent tutoring systems, conversational agents, and adaptive learning platforms—consistently improved student engagement metrics. Two randomized controlled trials showed low risk of bias, while four quasi-experimental studies showed moderate risk. AI-driven interfaces increased engagement by up to 25.13% in large-scale field tests. Personalized AI recommendations significantly improved learning performance and engagement, particularly for students with moderate motivation levels. AI tutors enabled students to learn more than twice as much in less time compared to traditional active learning approaches. Conclusions: The evidence demonstrates that AI technologies can effectively enhance student engagement and classroom interaction across diverse educational contexts. Randomized controlled trials provide the strongest evidence, while quasi-experimental studies show consistent positive effects despite moderate methodological limitations. Future research should prioritize rigorous experimental designs with preregistration, comprehensive reporting of missing data, and investigation of long-term effects and equity considerations.
DOI: http://doi.org/10.5281/zenodo.21509136
