Identifying the Current Status and Recent Trends of Digital Learning in the Republic of Korea through Keyword Network Analysis

Abstract

The purpose of this study is to identify recent trends in digital learning and propose areas for further research to contribute to its development and enhancement. To achieve this, keyword network analysis and structural equivalence analysis were employed to uncover thematic and structural advancements within media reports. The keyword analysis identified terms such as “digital,” “learning,” “AI,” “lifelong learning,” “support,” “operation,” “recruitment,” “education,” “data,” “implementation,” “learners,” and “digital textbooks.” By supplementing keyword weights based on importance, terms such as “learning,” “digital,” “AI,” “lifelong learning,” “support,” “recruitment,” “operation,” “education,” “data,” “learners,” “digital textbooks,” and “personalized learning” emerged as highly significant. Semantic network analysis was conducted to determine influential keywords in media reports on digital learning. Results revealed associations such as “digital-learning,” “students-recruitment,” “digital-transformation,” “learners-recruitment,” “lifelong learning-digital,” “AI-digital textbooks,” “AI-learning tools,” and “AI-digital” as closely related keyword pairs. Further analysis of correlations among key terms and the overall network led to the identification of four distinct clusters: personalized learning, digital textbooks, data-driven approaches, and lifelong learning. These findings indicate a growing trend in digital learning discourse centered on AI technologies, emphasizing aspects such as personalization, technological utilization, and data-driven approaches. Finally, we conducted a more in-depth analysis of the temporal changes, examining the relationships between keywords and their evolving patterns over time. Based on these trends, this study underscores the need for further academic review and research to address these evolving dynamics in digital learning.