Education big data and learning analytics: a bibliometric analysis

The increasing use of big data in education has created opportunities to gain new insights and improve learning. This study focuses on education big data and learning analytics, exploring how these processes can be leveraged to enhance the current educational system. The study aims to analyze trends and recommendations from publications in this field. Driven by the evolution of Industry 4.0 and the need for upgraded higher education programs, this research uses a bibliometric analysis to investigate the growth and key aspects of this area. The research questions address the distribution of publications over time (2012-2021), the most influential journals and authors, the most significant contributing countries, the dominant research keywords, and the most relevant subject areas within the field.

The introduction cites several sources highlighting the increasing importance of big data in education and the potential of learning analytics to transform traditional educational systems. These references underscore the large volume, variety, and velocity of data generated in education and the need for effective analysis to extract valuable insights and improve learning outcomes. The growing use of digital learning platforms is also noted as a key driver of the increased availability of educational data for analysis.

This study employed a bibliometric analysis method, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement template. The Scopus database was searched using the keywords "Education Big Data" and "Learning Analytics." The initial search yielded 885 documents. After applying inclusion/exclusion criteria (excluding 2022 publications, irrelevant subject areas, conference papers, reviews, editorials, and non-English articles), the final analysis included 250 publications. The VOSviewer software was used for data analysis and visualization to explore publication trends, influential authors and journals, key countries, keywords, and subject areas.

The analysis revealed a significant increase in publications on education big data and learning analytics between 2012 and 2021. IEEE Access was identified as the most relevant journal, followed by Lecture Notes in Educational Technology and Educational Technology and Society. Ben Williamson emerged as the most prolific author, with a high number of citations. The United States was the leading country in terms of publications, followed by the United Kingdom and China. The keywords "Big Data" and "Learning Analytics" showed the highest co-occurrence. Computer Science was the most prominent subject area, followed by Social Sciences. The analysis also mapped co-authorship relationships between countries and co-occurrence of keywords, providing a detailed visualization of the field's landscape.

The findings suggest a growing awareness and interest in the application of big data and learning analytics in education. The dominance of Computer Science reflects the technical aspects of data analysis and the development of tools and technologies, while the strong presence of Social Sciences underscores the importance of understanding the social and pedagogical implications of these technologies. The increasing number of publications and citations indicate a maturing field with significant potential for improving educational practices. The identified trends, such as the focus on learner behavior analysis, personalized learning, and the integration of AI and machine learning, highlight future directions for research and development.

This bibliometric analysis reveals a rapidly expanding field of research on education big data and learning analytics. The increasing number of publications, the identification of key journals and authors, and the leading countries and subject areas provide a valuable overview of the field. Future research should focus on further exploring the identified trends and expanding the scope of analysis to include other relevant databases. The integration of AI, machine learning, and data-driven decision-making within educational settings promises to transform learning and teaching practices.

This study's reliance on the Scopus database may limit the scope of the analysis, as other databases might reveal different insights. The use of only two keywords ("Education Big Data" and "Learning Analytics") might have narrowed the search results. Including more specific keywords could have yielded a more comprehensive analysis.