Educational Data Mining and Predictive Modeling in the Age of Artificial Intelligence: An In-Depth Analysis of Research Dynamics

Abstract

This article provides a comprehensive analysis of the research dynamics on the use of Educational Data Mining (EDM) and predictive modeling (PM) in the era of Artificial Intelligence (AI) based on the review of 793 articles published between 2000 and 2024 in the Scopus database. The study employs bibliometric analysis and systematic literature review to identify emerging trends, methodologies, and applications in these fields. The main objective of the study is to examine the primary methodologies and innovations within AI, especially in the context of EDM and PM. It highlights how these technologies can optimize the prediction of student performance, support personalized learning, and enable timely interventions through the analysis of student data. The study also examines the role of AI in improving teaching practices, ensuring that educators maintain control over the system and minimize potential biases. Furthermore, the article addresses the ethical implications of AI implementation in education, such as privacy protection, algorithm transparency, and equity in access to learning. The findings suggest that AI has the potential to significantly improve educational outcomes and optimize student tracking, resource allocation, and the overall effectiveness of educational institutions. The responsible implementation of AI in education is emphasized to ensure inclusive and fair environments for all students.