Enhancing Student Engagement and Learning Outcomes through AI-Powered Intelligent Tutoring Systems

Abstract

This study explores how Artificial Intelligence-powered Intelligent Tutoring Systems (ITS) enhance student engagement and learning outcomes in higher education. Grounded in constructivist, socio-cognitive, and self-determination theories, the research adopts a qualitative phenomenological research design. A purposive sample technique of twenty participants from higher education of Punjab was used. Data were collected through semi-structured interviews and analyzed using Braun and Clarke's six-step thematic analysis model to identify recurrent patterns and themes. Findings revealed four dominant themes: (1) personalized and adaptive learning pathways, (2) enhanced motivation and real-time feedback, (3) development of self-regulated learning skills, and (4) promotion of equity and accessibility in education. Collectively, these themes indicate that ITS fosters individualized learning experiences, intrinsic motivation, and learner autonomy, while supporting inclusive and data-driven pedagogical practices. However, concerns about data privacy, algorithmic bias, and institutional readiness remain critical for responsible implementation. The study concludes that ITS represents a transformative pedagogical innovation that aligns with learner-centred educational paradigms. It recommends further research on cross-cultural, longitudinal, and mixed-method investigations to deepen understanding of ITS effectiveness and ethical integration in higher education.

Keywords: Artificial Intelligence, Intelligent Tutoring Systems, Higher Education, Student Engagement, Personalized Learning, Qualitative Research, Adaptive Learning