Unveiling perceptions of students in online education through Tree Classifier analysis

Abstract

This article presents an analysis of students’ perceptions in online education using Tree Classifier analysis. The study involves a survey of 460 students who participated in online learning during the Covid-19 pandemic. With 49 questions, the survey aims to understand students’ experiences, challenges, support received, and preferences regarding online education. The main objective is to identify a cohort of students who prefer online study over face-to-face learning. Implementing the Random Forest algorithm in Python, this study extracts valuable insights into students’ perceptions of online education. Focusing on students in Almaty city, Kazakhstan, the research allows for potential comparisons with similar international studies to inform future research and policy recommendations for improving online, face-to-face, or blended learning formats. The findings shed light on factors influencing student satisfaction, engagement, and preference for online learning. Drawing on these insights, the study provides practical recommendations to enhance the online learning experience and address the identified challenges. This research contributes to the existing knowledge on online education, serving as a valuable resource for educators, policymakers, and researchers. It offers a comprehensive understanding of students’ perceptions and preferences in online education, based on the experiences of students in Almaty city. The results, coupled with comparative analyses from other countries, inform future research and facilitate improvements in online education delivery.