Date of Defense
14-4-2025 1:30 PM
Location
E1 - 1022
Document Type
Thesis Defense
Degree Name
Master of Science in Software Engineering
College
CIT
Department
Computer Science and Software Engineering
First Advisor
Dr. Salah Bouktif
Keywords
Learning Mode, Course Characteristics, CLO Achievement Prediction, Machine Learning, Hybrid Learning, Offline Learning, Online Learning, Educational Data Science, Recommendation System, Data-Driven Decision Making, Course Delivery Optimization
Abstract
The rapid transformation of educational delivery methods during the COVID-19 pandemic required institutions to transition between online, hybrid, and offline learning approaches, creating both challenges and opportunities for educators and students. While online and hybrid learning modes ensured continuity, their effectiveness across different course types remained uncertain. This thesis addresses this gap by developing a data-driven recommendation framework that predicts Course Learning Outcome (CLO) achievement and recommends the most appropriate learning mode (online, hybrid, or offline) along with instructional tools based on course characteristics.
This study analyzed 100 undergraduate and postgraduate courses from the College of Information Technology (CIT) at the United Arab Emirates University (UAEU), offered across 1200 sections, covering academic periods from Fall 2020 to Fall 2023, thereby incorporating both pandemic and post-pandemic instructional transitions. The dataset derived from official course portfolios, captures key attributes such as teaching methodologies, assessment strategies, practical engagement, and CLO achievement trends across three departments: Computer Science & Software Engineering (CSSE), Computer & Network Engineering (CNE), and Information Systems & Security (ISS).
A machine learning-based approach was utilized to predict CLO achievement rates, comparing multiple models, including Linear Regression and Random Forest, with Gradient Boosting Regressor emerging as the most effective model. Additionally, a rule-based recommendation system was designed to translate predictive insights into structured instructional strategies, ensuring that courses emphasizing hands-on engagement receive practical learning environments, while theoretical and analytical courses are optimized for hybrid or online settings.
The findings of this study offer a structured approach to data-driven academic planning, enabling institutions to align course delivery methods with student learning needs. This study contributes to the growing field of educational data science, illustrating how predictive analytics and recommendation systems can facilitate evidence-based decision-making to improve learning effectiveness, instructional design, and curriculum planning in higher education.
Included in
A DATA-DRIVEN RECOMMENDATION SYSTEM FOR SELECTING THE APPROPRIATE MODE OF LEARNING AND INSTRUCTIONAL TOOLS BASED ON COURSE CHARACTERISTICS
E1 - 1022
The rapid transformation of educational delivery methods during the COVID-19 pandemic required institutions to transition between online, hybrid, and offline learning approaches, creating both challenges and opportunities for educators and students. While online and hybrid learning modes ensured continuity, their effectiveness across different course types remained uncertain. This thesis addresses this gap by developing a data-driven recommendation framework that predicts Course Learning Outcome (CLO) achievement and recommends the most appropriate learning mode (online, hybrid, or offline) along with instructional tools based on course characteristics.
This study analyzed 100 undergraduate and postgraduate courses from the College of Information Technology (CIT) at the United Arab Emirates University (UAEU), offered across 1200 sections, covering academic periods from Fall 2020 to Fall 2023, thereby incorporating both pandemic and post-pandemic instructional transitions. The dataset derived from official course portfolios, captures key attributes such as teaching methodologies, assessment strategies, practical engagement, and CLO achievement trends across three departments: Computer Science & Software Engineering (CSSE), Computer & Network Engineering (CNE), and Information Systems & Security (ISS).
A machine learning-based approach was utilized to predict CLO achievement rates, comparing multiple models, including Linear Regression and Random Forest, with Gradient Boosting Regressor emerging as the most effective model. Additionally, a rule-based recommendation system was designed to translate predictive insights into structured instructional strategies, ensuring that courses emphasizing hands-on engagement receive practical learning environments, while theoretical and analytical courses are optimized for hybrid or online settings.
The findings of this study offer a structured approach to data-driven academic planning, enabling institutions to align course delivery methods with student learning needs. This study contributes to the growing field of educational data science, illustrating how predictive analytics and recommendation systems can facilitate evidence-based decision-making to improve learning effectiveness, instructional design, and curriculum planning in higher education.