ADVANCING PERSONALIZED LEARNING THROUGH LEARNING ANALYTICS: A SELF-DETERMINATION THEORY PERSPECTIVE

This article examines how learning analytics (LA) can be used to operationalize personalized learning in real classroom conditions through the lens of Self-Determination Theory (SDT). Drawing on international research, it synthesizes how LA supports personalization by enabling scalable diagnosis of learners’ needs, informing adaptive instructional support, and improving the timeliness and specificity of formative feedback. At the same time, the review highlights recurring implementation barriers, particularly the difficulty of translating dashboard indicators into feasible instructional actions, as well as the ethical and governance requirements associated with collecting and processing learner data. Using SDT as a guiding framework, the paper discusses how LA-enabled personalization can strengthen competence through mastery-oriented guidance, while potentially undermining autonomy and relatedness when personalization becomes overly performance-driven or surveillance-like and when social learning opportunities are reduced. To address these tensions, the article proposes an SDT-aligned implementation pathway that links pedagogical purpose, responsible data use, interpretable insights, actionable instructional options, and iterative refinement based on both learning outcomes and learner experience. The paper concludes that LA can make personalization more effective and humane when analytics is pedagogically aligned, ethically governed, and designed to protect students’ psychological needs alongside academic goals.