Personalization-based deep hybrid E-learning model for online course recommendation system

Area of Science:

• Artificial Intelligence
• Machine Learning
• Educational Technology

Background:

• Online learning platforms require effective course selection for student success.
• Traditional methods often lack personalized recommendations, leading to suboptimal course enrollment.
• Deep learning offers automated solutions for complex analytical tasks.

Purpose of the Study:

• To develop a hybrid deep learning (HDL) model for an online learning platform's course recommendation system.
• To enhance student decision-making in course selection through informed recommendations.
• To facilitate optimal class scheduling for universities by predicting student course preferences.

Main Methods:

• A hybrid deep learning (HDL) framework was developed, integrating Convolutional Neural Network (CNN), Residual Network (ResNet), and Long Short-Term Memory (LSTM).
• The model analyzes student data to predict interest in future courses.
• A recommendation system was designed based on this hybrid framework.

Main Results:

• The proposed HDL model effectively recommends appropriate courses to students.
• The system encourages informed decision-making for course selection.
• It aids learners in making correct choices for their studies.

Conclusions:

• The developed hybrid deep learning recommendation system improves the course selection process in online learning.
• This approach supports both students in choosing courses and universities in scheduling.
• The integration of CNN, ResNet, and LSTM offers a robust solution for educational recommendation systems.