AN EFFECTIVE DATA MINING APPROACH FOR ASSESSING STUDENT’S SATISFACTION IN ONLINE EDUCATION DURING COVID-19 PANDEMIC

Abstract

The advent of the COVID-19 outbreak has caused widespread public-health concerns. As a result of these emergency conditions, several governments have opted to implement lockdowns to reduce social interaction and minimize infection. COVID-19 has significantly impacted Higher Education Organizations (HEOs). Many unorthodox educational methods are proposed to ensure the continuation of the learning system in light of the effects of this pandemic and the necessity for alternative remedies. Online Education (OE), also based on learning together in a synchronous or asynchronous environment by employing various equipment, including mobile devices, Computers, and so forth, for Internet access, was among the options. All education systems are primarily concerned with boosting students' academic achievement to improve the overall standard of teaching. In this regard, Educational Data Mining (EDM) seems to be an expeditiously growing field of research that employs the significance of Data Mining (DM) ideas to assist the education system in determining valuable information just on Student Satisfaction Learning (SSL) with both Online Learning procedure (OL) as during COVID-19. Various approaches have been explored using EDM to forecast students' behaviors to provide the optimum educational settings. As a result, Feature Selection (FS) was commonly used to find one of the most indicates. the status of characteristics with the least cardinality. For COVID-19 to find accuracy result in this research KNN and SVM algorithm used by using modified data set from Kaggle. Results showed 79.9% precision of education level wise prediction using KNN, 73.7% precision of devices wise prediction using KNN and 88.5% precision of educational level wise predication using SVM, 73.8% precision of device wise prediction using SVM which is showing that the proposed model is significant.