Efficiency of stacked ensemble learning for student's adaptivity classification to online education

It is necessary to know the extent to which students adapt to online learning, especially after the Corona pandemic. Online and e-learning have become essential parts of the educational process. It is important to try to improve students' adaptation to this type of education to obtain the best results. Expanding existing knowledge of students' ability to adapt to online learning is the aim of this study. Machine learning techniques have been exploited to develop various models and compare their results in order to obtain the best technology and the most powerful model that can be used to improve the educational process. Four different models were developed, each model contained algorithms for a type of machine learning (Bagging, boosting, and Stacking), in addition to a model that contained a variety of algorithms (single and ensemble learning). These models used four methods of selecting features, which are: Relief F, ANOVA, Information Gain, and Chi-square. K = 10-fold was used with classifiers in all models in this study. The accuracy reached 0.866 % by Gradient Boosting algorithm using the Chi-square technique. While the highest value of accuracy obtained by the stacked learning by employing Boosting classifiers in level-0 and Logistic Regression in level-1 using the Chi-square technique was 0.874%.