An Investigation on Students’ Level of Adjustment to Online Education with C5.0 Decision Tree Algorithm

Abstract

This study aims to determine the independent variables that have a significant effect on the level of students’ adaptation to online education and their order of importance. Relational screening model was used in the study. Adaptability Level in Online Education dataset provided by Kaggle repository constitutes the main data source for this study. C5.0 decision tree algorithm was used to analyze the data. It was found that that 51,867% of the students had a moderate level of adaptation to online education, while 39,834% had low, and 8,299% had a high level adaptation. The findings indicate that students’ level of adaption to online learning is insufficient. We also found that the variable that best explains the online education compliance levels is daily class duration. “Financial condition” was found as the best explanatory variable of the cluster formed by the students whom “daily class duration” was between “1-3 hours”. “Age” was found as the best explanatory variable of the cluster formed by the students whom “daily class duration” was between “1-3 hours” and has “financial condition” of “poor”, “mid” and “rich”.