Educational Data Mining Applications and Techniques

Abstract

Educational data mining (EDM) uses data mining techniques to analyze huge amounts of student data in the educational environments. The main purpose of EDM is to analyze and solve educational issues and, consequently, improve educational processes. With the emergence of EDM applications in the educational environments, several techniques have been identified to implement these applications. This paper reviews the relevant studies in EDM including datasets and techniques used in those studies and identifies the most effective techniques. The most prevalent applications include predicting student performance, detecting undesirable student behaviors, grouping students and student modeling. These applications aim to help decision makers in the educational institutions to understand student situations, improve students' performance, identify learning priorities for different groups of students and develop learning process. The prediction accuracy is selected as the evaluation criteria for the effectiveness of educational data mining techniques. The results show that Bayesian Network and Random Forest are the most effective techniques for predicting student performance, Social Network Analysis is the best technique for detecting undesirable student behaviors, Clustering and Social Network Analysis are the most effective techniques for grouping students and student modeling, respectively. This study recommends conducting more comprehensive and extended studies to evaluate the effectiveness of EDM techniques with an extended evaluation criteria.

A Proposed Framework for Big Data Analytics in Higher Education

“…To attain the data regarding education of student, the EDM can be used which will help to improve the educational processes and monitor the leaning for the feedback. The information can be employed to give suggestions to adjust with the leaning attitude of the students depending on their learning patterns along with the unexpected leaning attitudes [31]. Like, the way of how the learning tasks of students were anticipated with the usage of kmeans clustering algorithm according to Reference [30].…”

“…All the types of academic data mining could be classified into five categories: prediction, clustering, relationship mining, discovery with models, and distillation of data for human judgment according to [35]. The initial three groups are generally considered by the EDM research team while, the last two groups are just dominant in the area of academic data mining [31]. The term prediction, in the EDM targets to show case the educational finding from the other information factors.…”

“…Many colleges and universities have proved that analytics may help an institution considerably advance in such important areas as resource allocation, student achievement, and financial planning and administration. When leaders of institutions of HEd read about innovations occurring at other institutions as a result of BD analytics, they begin looking for methods to implement analytic programs in their own institutions [31]. Several studies, including the McKinsey Global Institute Report on BD [33], have found that the most developed regions, such as Europe, have the most potential to create value through the use of BD.…”

Educational Data Mining, Student Academic Performance Prediction, Prediction Methods, Algorithms and Tools: An Overview of Reviews

“…If the term performance is disaggregated from the phrase student academic performance, it embodies achievement in relation to assignments and courses, continuous progress in programmes, and a successful completion of programmes [2,18]. Moreover, it entails persistence, retention, progression, wastage) [37], and success or progress [38,39]. In this sense, student academic performance should be seen in the same way as student academic achievement [14].…”

A Comparison of EDM Tools and Techniques

“…In 2020, the study [48] by Fatima Alshareef et al reviewed the related researches in EDM, including applications and techniques, and identified the best algorithm for each of the EDM applications. The authors had relied on the right prediction accuracy and use it as a guide for identifying effective techniques.…”