Mapping research on digital adaptive learning in education: a bibliometric approach

Cogent Education, 2026

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.1080/2331186x.2026.2699507
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Artificial intelligence and related digital technologies have become a major driver of research on adaptive learning, giving rise to a broad body of literature across diverse educational contexts. This study presents a bibliometric analysis of publications on adaptive learning from 1977 to mid-2025 using metadata extracted from the Scopus database. Publication trends show sustained growth, particularly after 2015, reflecting increasing interest in personalised and technology-enhanced learning. Researchers and institutions from the United States, China, and Taiwan emerge as leading contributors, while collaboration patterns reveal both regional hubs and expanding international networks. Co-citation analysis identifies an intellectual core grounded in learner-centred adaptivity, educational theory, cognitive science, and instructional design. Thematic mapping highlights the convergence of instructional design, educational psychology, and emerging AI concepts. Overlay visualisation of keyword co-occurrence indicates that AI-related terms are associated with more recent average publication years than foundational concepts, reflecting their growing prominence in the literature. However, a content analysis of 50 recent abstracts (2023–2025) showed that only 54% of AI-tagged papers reported actual AI implementation. These findings suggest a continuing thematic shift toward AI-related discourse rather than a fully established transformation of adaptive learning research.