Multi-Dimensional Analysis to Predict Students’ Grades in Higher Education

Eslam Abou Gamie, Samir Abou El-Seoud, Mostafa Salama, Walid Hussein


This work enhances the analysis of the student performance in the high education level. This model categorizes the features according to their relativeness to the teaching style and to the student activities on an Electronic Learning system. Several new features are proposed and calculated in each of these two categories/dimensions. This approach applies an extra level of machine learning that analyses the data based on a set of dimensions, and each dimensions includes a set of features. The prediction analysis is applied on each dimension separately based on a different classifiers. The best fitting classifier to each dimension ensures the enhancement of the local analysis accuracy and though enhances overall global accuracy. The accuracy of prediction of the student is enhanced to 87%. This study allows the detection of the correlation the features in different dimension. Furthermore, a study is applied on the scanned text documents for extracting and utilizing the features that represent the student uploads.


Data mining; education data mining; MOODLE; feature selection, correlation analysis; learning activities; pedagogical approaches; classification

Full Text:


Copyright (c) 2019 Samir Abou El-Seoud, Eslam Abou Gamie

International Journal of Emerging Technologies in Learning (iJET) – eISSN: 1863-0383
Creative Commons License
Scopus logo Clarivate Analyatics ESCI logo EI Compendex logo IET Inspec logo DOAJ logo DBLP logo Learntechlib logo EBSCO logo Ulrich's logo Google Scholar logo MAS logo