Examining Student Psychology Profile Modeling Methods Based on Machine Learning Programme

Abstract

Propose: This study aims to analyzed global perspective of the student profile has a global perspective model may be created.

Theoretical Framework: Computer-aided education (CAE) techniques used for various purposes, such as predicting failure, dropout, and academic achievement, have to be researched, and the prominent features employed. The Decision Tree is the most commonly used method in research studies. Personal and online behavioral aspects are taken into account when students are rated.

Methodology: An experiment was conducted to reinforce the survey results using the most recent machine learning techniques applied to the same datasets.

Findings: According to the survey results, the best outcomes were achieved using a decision tree.

Implications: ICT developments have led to an increase in online learning and the development of e-recommendation services, online recruiting, and other educational tools.

Value: Advances in Machine Learning make it possible to tailor services for students based on their specific requirements and preferences. Student profile modeling has come a long way in the previous four years thanks to advances in machine learning approaches, which we detail in this work.