Investigation of the Educational Performance on the Revolutionary Philosophical Electoral Online Learning Platform Centred on Deep Learning

Abstract

Modern methods, strategies, and applications from educational data mining significantly contribute to the advancement of the learning environment. The most recent development offers useful resources for analyzing the educational environment of students by examining andusing data mining and machine learning methods to analyse educational data. In today's extremely competitive and complex world, academic institutions function. University administrators frequently struggle with performance evaluation, high-quality instruction, performance evaluation methodologies, and future course of action. In order to address issues that students face while pursuing their education, these colleges must establish student intervention strategies. This systematic review examines the pertinent EDM literature from 2009 to 2021 that relates to detecting kids at risk and dropouts. The review's findings showed that a variety of Deep Learning techniques are utilized to comprehend and address the fundamental issues, including forecasting students who are at danger of dropping out of school and students who will drop out altogether. Furthermore, the majority of studies incorporate data from online learning platforms and databases of student institutions and universities. When it comes to forecasting at-risk pupils and dropout rates, ML techniques have been shown to be crucial. This has improved the students' performance.