AI-Driven Personalized Learning in Higher Education: A Systematic Review Through the Lens of Bloom’s Taxonomy

Abstract

Background: Artificial intelligence has increasingly been adopted to support personalized learning in higher education; however, existing research remains fragmented with limited synthesis of how AI-driven personalization aligns with cognitive learning outcomes, particularly those defined by Bloom’s taxonomy. While generative AI has gained attention, its pedagogical role relative to earlier analytics-based and intelligent tutoring approaches remains insufficiently examined. Method: This study presents a systematic literature review conducted in accordance with PRISMA-2020 guidelines. Peer-reviewed studies published between 2015 and 2025 were identified through Scopus, Web of Science, IEEE Xplore, ACM Digital Library, ERIC, SpringerLink, and ScienceDirect. Following screening and quality assessment, 25 studies were included for synthesis. Key Findings: The analysis indicates that AI-driven personalization predominantly supports lower-order cognitive processes, including remembering, understanding, and application. Learning analytics and intelligent tutoring systems primarily enable adaptive feedback and content sequencing, while generative AI shows emerging potential for supporting higher-order cognition, though empirical evidence remains limited. Implications: The findings highlight the need for cognitively aligned AI system design in higher education. Future AI-based learning tools should explicitly integrate Bloom’s taxonomy to ensure pedagogical coherence, transparency, and meaningful support for higher-order learning outcomes.