USING MACHINE LEARNING ALGORITHMS TO ANALYZE FACTORS INFLUENCING ACCEPTANCE OF E-LEARNING

A C TThe COVID-19 pandemic has brought about measures like social distancing and lockdowns, significantly affecting educational institutions.Universities were forced to adapt to online or hybrid teaching models to continue academic activities.This shift disrupted traditional education, requiring students, educators, and institutions to adjust.Identifying key factors influencing elearning systems is challenging and requires thorough evaluation.To address this, we propose a solution using the K-means clustering algorithm to analyze student data.By applying machine learning-based classification methods, this model identifies the best-fit learning approach for each student, ensuring a more tailored and effective e-learning experience.The research focused on a sample of 605 students from various schools across India, aiming to assess the impact of AI-driven social learning networks, personalized learning portfolios, and tailored learning environments.The findings revealed a strong correlation between these AI-based tools and the students' perceived usefulness and ease of use in their educational experiences.The experiment resulted in an accuracy rate of 82.52% for predicting the suitable learning method for students based on the identified factors.