Beyond the Classroom: Understanding the Evolution of Educational Data Mining With Key Route Main Path Analysis

Abstract

Educational data mining (EDM) enhances the educational system by uncovering hidden patterns of academic data. The discipline of EDM has grown rapidly and produced numerous publications, leading to knowledge dissemination among researchers. This research aims to understand the EDM field literature by examining the citation network of significant publications. This research utilizes a quantitative approach based on citation main path analysis (MPA) to analyze 1009 Web of Science (WoS) publications between 1988 and 2023. The study uncovers 22 significant publications that have shaped the knowledge diffusion trajectories of EDM. The research reveals that EDM has undergone three phases of evolution, each of which represents a substantial shift in the research focus: automated adaptation, leveraging human decision, and advanced predictive analytics. Unlike previous EDM reviews, this study applies a novel approach using multiple global MPA, uncovering five key sub-research areas: student performance, early warning, learning behavior, transfer learning, and dropout. Notably, recent trends emphasize a growing focus on student performance. The primary contribution of this paper lies in its comprehensive mapping of EDM's developmental trajectory, offering an understanding of its diverse research trends. By elucidating these patterns and emerging areas, this study not only enriches the existing literature but also identifies unexplored topics that can guide future research directions, distinguishing itself from other EDM reviews by offering a more systematic and data-driven analysis of the field's evolution.