<![CDATA[Purpose: This study analyzes the systematic integration of Artificial Intelligence (AI) and Learning Analytics (LA) within higher education Learning Management Systems (LMS). It aims to identify adaptive personalization models, scrutinize pressing ethical and algorithmic challenges, and map future instructional paradigms for tertiary learning environments. Method: Employing a PRISMA-compliant systematic literature review methodology, this research evaluated 15 peer-reviewed empirical articles published between 2020 and 2025. Relevant studies were systematically retrieved and synthesized from Scopus, Web of Science, and IEEE Xplore, focusing explicitly on higher education contexts. Findings: Results demonstrate that AI morphs the traditional LMS into an active "smart learning partner." Machine Learning algorithms accurately identify at-risk students within the initial four weeks, while automation reduces faculty administrative workloads by 30%. However, chief impediments remain algorithmic data bias and faculty analytical literacy gaps. Practical implications: Higher education institutions must engineer intuitive, visual data dashboards and deploy comprehensive digital literacy training for lecturers, empowering them to translate predictive insights into timely, effective pedagogical interventions. Originality/value: This study propounds a unified socio-technical framework that transcends isolated single-tool evaluations. It underscores the urgent exigency for Explainable AI (XAI) regulations and redefines modern educational technology as an active knowledge co-creator in academia.]]>
Copyrights © 2025
