E-Learning Readiness Assessment Using Machine Learning Methods

Assessing e-learning readiness is crucial for educational institutions to identify areas in their systems needing improvement and develop strategies enhance students’ readiness. This paper presents an effective approach assessing by combining the ADKAR model machine learning-based feature importance identification methods. The motivation behind using learning approaches lies ability capture nonlinearity data flexibility as data-driven models. study surveyed faculty members students Economics at Tlemcen University, Algeria, gather based on model’s five dimensions: awareness, desire, knowledge, ability, reinforcement. Correlation analysis revealed a significant relationship between all dimensions. Specifically, pairwise correlation coefficients reinforcement are 0.5233, 0.5983, 0.6374, 0.6645, 0.3693, respectively. Two algorithms, random forest (RF) decision tree (DT), were used most important factors influencing In results, knowledge consistently identified factors, with scores of (0.565, 0.514) (0.170, 0.251) RF DT Additionally, SHapley Additive exPlanations (SHAP) values explore further impact each variable final prediction, highlighting influential factor. These findings suggest that universities should focus enhancing abilities providing them necessary increase e-learning. provides valuable insights into university