Artificial Intelligence in Educational Measurement: A Bibliometric Review (1997 to 2024)

Artificial Intelligence (AI) is increasingly influencing measurement practices across fields such as health sciences, diagnostics, and psychology by enhancing accuracy, efficiency, and personalization. In the educational domain, however, the application of AI in assessment remains relatively underdeveloped, despite its significant potential to support adaptive systems and individualized feedback. This bibliometric review analyzes 921 peer-reviewed articles published between 1997 and 2024 to examine how AI contributes to the evolution of educational measurement. Through citation, co-citation, and keyword co-occurrence analyses, the study identifies influential publications, maps the intellectual structure of the field, and explores emerging thematic directions. Results indicate a substantial growth in research output after 2019, driven by advances in machine learning, natural language processing, and big data analytics. Foundational contributions from health and computer sciences, such as deep learning methods and open-source tools like Scikit-learn, have significantly influenced educational technologies. Three core themes are identified: the technical foundations of AI, cross-disciplinary applications in cognitive and medical diagnostics, and ethical and policy challenges related to AI implementation in education. Global collaboration is prominent, with leading contributions from the United States and China and increasing participation from Malaysia, Pakistan, and Nigeria. The review highlights the interdisciplinary nature of AI in educational measurement and calls for responsible, scalable applications to support inclusive and personalized learning environments