STUDENT CLASSIFICATION IN HIGHER EDUCATION: LITERATURE REVIEW OF MODELS, APPROACHES, AND CHALLENGES

ABSTRACT

This paper explores student classification in higher education, addressing gaps in how diverse student characteristics are integrated into classification models. It focuses on personality traits, learning styles, achievement emotions, and player typologies, offering a structured review of how these characteristics are used to define student types. The aim is to support efforts toward personalized learning, early identification of at-risk students, and improved academic support systems. A qualitative, literature-based approach is employed to analyze student classification models and techniques. The paper reviews academic works across various contexts, examining how different student characteristics are used, what classification methods are applied (e.g., machine learning, ontology-based), and the models’ educational settings. Key strengths, limitations, and trends are synthesized. The review finds that existing works often lack consistency, generalizability, and holistic integration of student characteristics. Many approaches rely on learning theories or algorithmic techniques without offering comprehensive, scalable solutions. A shift toward multi-dimensional, adaptive models is evident, though ethical, technical, and contextual challenges persist. This study offers a structured synthesis of student classification literature, organized around four key dimensions of student characteristics. It differs from previous reviews by detailing specific models, their applications, and associated student types. The findings contribute to the advancement of ethical and adaptive classification systems and identify future research directions for developing more effective and equitable educational technologies.