Year: 2026
Type: article
Abstract: This article presents a methodological framework for designing intelligent tutoring systems (ITS) for personalized programming education in higher education. The study addresses a persistent problem in programming courses: students enter with heterogeneous prior knowledge, progress at different speeds, and require different kinds of feedback when solving coding problems. The proposed ITS model integrates five core layers: learner diagnosis, student modeling, domain modeling, pedagogical decision-making, and adaptive feedback. The methodology combines pedagogical analysis, learning analytics, diagnostic programming tasks, student modeling, and a quasi-experimental design with control and experimental groups. Model-based results indicate that a personalized ITS can improve programming competence by strengthening theoretical understanding, algorithmic thinking, code-writing quality, debugging skills, and reflective self-regulation. The article also provides a conceptual model, assessment rubrics, experimental tables, and implementation recommendations for institutions planning to introduce ITS-supported programming instruction. The contribution of the study lies in connecting intelligent tutoring architecture with programming-specific competence indicators and in proposing a practical design model that supports personalized learning paths, real-time feedback, and teacher-facing analytics.
Author: Altmisheva Iroda Mavlyanovna
Institution: Gulistan State University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: diamond
OpenAlex ID: W7221293460
