Abstract:
Massive Open Online Courses (MOOCs), Virtual Learning Environments (VLEs), and Learning Management Systems (LMS) make it possible for millions of students to follow their interests in learning without regard to time or location constraints. However, online learning environments have downsides, including poor student engagement, high dropout rates, the need for students to selfregulate their conduct, and the requirement that students establish their own academic goals. In this research, we propose a hybrid machine-learning predictive model that evaluates the challenges faced by students who are at risk. The hybrid model gives teachers the ability to initiate intervention to encourage students to increase the amount of time they spend studying and improve their academic performance. Moreover, the proposed hybrid machine learning prediction model uses student study characteristics to define students' learning behavior. When comparing the performance of hybrid models to various machine learning algorithms, many metrics such as accuracy, precision, support, and f-score are utilized. Our hybrid machine learning model achieves the best results in terms of accuracy, precision, recall, support, and the f-score metric. In addition, the proposed hybrid machine learning prediction model can help teachers identify students who are at risk of dropping out of school, provide rapid intervention, and reduce the number of students who withdraw from their studies.
Page(s):
61-61
DOI:
DOI not available
Published:
Journal: Abstract Book on International Conference on Food and Applied Sciences (ICFAS-23) 3-5 August 23, Volume: 0, Issue: 0, Year: 2023