A New Approach to Machine Learning Algorithms in Adaptive E-Learning Systems

Abstract

Introduction: Adaptive e-Learning denotes a collection of methodologies aimed at providing online learn-ers with a personalized and distinctive experience, ultimately intended to enhance their performance. Adaptive e-Learning operates on the premise that each learner possesses dis-tinct characteristics, including varied backgrounds, educational requirements, and learning preferences.

Objectives: The aim of Adaptive e-Learning is to identify individual differences and convert them into pertinent information and training methodologies tailored for each student. This paper explores the used of machine learning (ML) and deep leaning techniques in crafting personalized learning experiences within adaptive e-learning systems, especially estimated the learning style.

Methods: It highlights key algorithms employed for learner modeling, recommendation, assessment, and improved student outcomes by focused on the style of learning for the students. First step, we used an educational dataset that are related to the learning style for 1,210 students. Then, the preprocessing steps were applied on the dataset like checking missing values, and turning object columns type to categorical for easing the transformation process.

Results: The deep learning techniques that were used are deep neural network (DNN), while the ML techniques are Random Forest, XGBoost, AdaBoost, and Logistic Regression. To assess these algorithms, the accuracy, precision, recall, and f1-score. The finding of this paper for all the algorithms are as follows: DNN (91, 89, 90, 90), RF (83, 83, 83, 83), LR (89, 90, 90, 90), XGB (83, 83, 83, 83), and Ada (86, 87, 86, 86). We have shown that the DNN gave the best prediction of learning style compared with the others.

Conclusions: investigating the impact of feature extraction and selection, as highlighted in previous studies, could contribute to refining the accuracy and effectiveness of the system.