From cognitive levels to adaptive algorithms: bloom's taxonomy in the design of adaptive learning management systems

Abstract

Adaptive learning management systems (LMS) increasingly personalize instructional content and difficulty, yet designers frequently prioritize technical convenience over explicit pedagogical theory. This scoping review examines how Bloom's Taxonomy — one of the most widely used frameworks for structuring cognitive learning objectives — has been operationalized in the design of adaptive mechanisms within LMS and intelligent tutoring system research. I identified literature through Google Scholar, Scopus, and Consensus, covering foundational pedagogical sources without date restriction and technical adaptive-learning sources published between 2015 and 2026. The review finds that Bloom's Taxonomy has been applied to adaptive system design only in isolated instances, most notably for content-complexity matching and scaffolding-difficulty calibration, without a systematic account of how the taxonomy's full hierarchy corresponds to distinct classes of adaptive design. Building on these precedents, the review proposes a working-hypothesis mapping between the six cognitive levels of Bloom's Taxonomy and six classes of adaptive mechanisms, ranging from rule-based branching logic at the remembering level to personalized, open-ended learning-pathway generation at the creating level. Two of the six correspondences have direct empirical precedent in existing systems; the remaining four are proposed analogically and require further empirical validation. The proposed framework offers a starting structure for grounding adaptive LMS design decisions in cognitive learning theory; future research should test it empirically and explore institutional implementation.