A Systematic Literature Review of AI-Driven Intelligent Tutoring Systems in Engineering Education: Emphasizing Personalization, Feedback, and Student Monitoring
B. A. Rodrigues, Rui Pinto, Gil Gonçalves
Abstract
Artificial Intelligence (AI) technologies are reshaping educational environments, particularly through Intelligent Tutoring Systems (ITS) that enable personalized instruction and real-time adaptability. This Systematic Literature Review (SLR) explores the application of AI-powered ITS in engineering education, a field where learners often struggle with abstract and technically complex content. Guided by the PRISMA methodology, the review analyzes 46 peer-reviewed studies featuring components such as Natural Language Processing (NLP), adaptive learning pathways, real-time feedback, and learner progress tracking. Unlike prior reviews that emphasize general pedagogical frameworks, this work offers three key contributions: a focused synthesis of AI-based ITS solutions tailored to engineering education; a novel analysis of underexplored feature combinations, such as the integration of teacher-facing analytics with student-facing personalization; and the identification of research gaps in dual-user support for both learners and instructors. These findings provide actionable insights for researchers and developers aiming to design next-generation ITS platforms that are pedagogically robust, technically scalable, and aligned with the discipline-specific demands of engineering education.