Systematic Review of Educational Data Mining for Student Performance Prediction using Bibliometric Network Analysis (SeBriNA)

Abstract

Data mining has emerged as a way of working with large amounts of data in various fields of technology that produce data types quickly and correctly. In particular, emerging technologies such as data mining (DM), machine learning (ML), and big data are utilized to predict student performance. This paper uses bibliometrics to give a complete picture of the studies that have been done on how DM technologies are used in Educational Data Mining (EDM). The study aims to determine which DM techniques are most often used to predict student performance and how the field of DM for education to predict student performance has changed over time. To investigate the topic, we used both qualitative and quantitative methods. We used the Scopus database to find relevant articles published in scientific journals, and this study includes 130 articles published between 2015 and 2021. Also, we used the bibliometric library and bibliophily features for the bibliometric analysis. Our findings show that various EDM technologies are used at each stage of student performance prediction. Several supervised ML algorithms are used for prediction. The bibliometric analysis shows that EDM for predicting student performance is a proliferating field of science. Scientists from all over the world are keen to conduct research and collaborate in this interdisciplinary scientific field.