USING ARTIFICIAL INTELLIGENCE TECHNOLOGIES TO ANALYZE STUDENTS’ BEHAVIOUR IN A DIGITAL LEARNING ENVIRONMENT

Abstract

Digital learning environments produce substantial quantities of behavioral data; however, a significant portion of this information remains unconverted into prompt pedagogical insights. This article explores the integration of artificial intelligence (AI) technologies into learning analytics for the analysis of student behavior within a digital learning environment. A conceptual AI-driven framework is introduced that integrates log data, interaction traces, and assessment results to deduce patterns of engagement, self-regulation, and dropout risk. Supervised and unsupervised machine learning, sequence modeling, and natural language processing are aligned with fundamental monitoring and prediction functions. Human-centered design, data protection, and the risk of algorithmic bias are given special attention. The article contends that AI-driven behavioral analytics can significantly improve student support and instructional quality when transparency, teacher autonomy, and ethical safeguards are prioritized in the design process rather than being considered as mere afterthoughts.