Date of Defense
12-6-2025 11:00 AM
Location
E1-1013
Document Type
Thesis Defense
Degree Name
Master of Science in Software Engineering
College
CIT
Department
Computer Science and Software Engineering
First Advisor
Prof. Nazar Zaki
Keywords
Automated academic advising, KGs, ML, Personalized academic plans, Course demand prediction, LLMs.
Abstract
Academic advising plays a critical role in helping students make informed decisions, improve academic performance, and successfully navigate their university journey. However, with increasing university enrollment, traditional advising methods often struggle to scale, leading to student frustration and overburdened advisors. Additionally, designing course offerings that match student demand is a complex and error-prone process involving multiple stakeholders. To address these challenges, this thesis proposes an automated, data-driven system for generating personalized academic plans for students. The primary aim of this thesis is to develop a system that reduces students' dependency on advisors while simultaneously providing accurate estimates of course demand to assist in academic planning for upcoming semesters. The proposed system operates in two phases. In the first phase, Knowledge Graphs (KGs) are used to model relationships between courses, prerequisites, and student progress. In the second phase, Machine Learning (ML) techniques and Large Language Models (LLMs) are integrated to further personalize course recommendations. The system is designed to ensure logical course progression while adhering to university-specific academic policies, with a case study conducted at the United Arab Emirates University (UAEU). The generated academic plans demonstrate up to 70\% similarity when compared to the generic degree plans provided by the university and show an average of 80\% similarity when compared to actual plans followed by graduated students. This work introduces a hybrid system combining Knowledge Graph modeling with Machine Learning personalization for academic advising, offering a scalable and interpretable solution that aligns course planning with student needs and institutional constraints. This thesis addresses the scarcity of research applying Knowledge Graphs for personalized academic planning in universities, bridging the gap between traditional advising practices and automated, data-driven recommendation systems tailored to individual student backgrounds.
Included in
ADVANCING ACADEMIC ADVISING WITH KNOWLEDGE GRAPHS: INTEGRATING MACHINE LEARNING AND LLMS FOR PERSONALIZED COURSE PLANNING
E1-1013
Academic advising plays a critical role in helping students make informed decisions, improve academic performance, and successfully navigate their university journey. However, with increasing university enrollment, traditional advising methods often struggle to scale, leading to student frustration and overburdened advisors. Additionally, designing course offerings that match student demand is a complex and error-prone process involving multiple stakeholders. To address these challenges, this thesis proposes an automated, data-driven system for generating personalized academic plans for students. The primary aim of this thesis is to develop a system that reduces students' dependency on advisors while simultaneously providing accurate estimates of course demand to assist in academic planning for upcoming semesters. The proposed system operates in two phases. In the first phase, Knowledge Graphs (KGs) are used to model relationships between courses, prerequisites, and student progress. In the second phase, Machine Learning (ML) techniques and Large Language Models (LLMs) are integrated to further personalize course recommendations. The system is designed to ensure logical course progression while adhering to university-specific academic policies, with a case study conducted at the United Arab Emirates University (UAEU). The generated academic plans demonstrate up to 70\% similarity when compared to the generic degree plans provided by the university and show an average of 80\% similarity when compared to actual plans followed by graduated students. This work introduces a hybrid system combining Knowledge Graph modeling with Machine Learning personalization for academic advising, offering a scalable and interpretable solution that aligns course planning with student needs and institutional constraints. This thesis addresses the scarcity of research applying Knowledge Graphs for personalized academic planning in universities, bridging the gap between traditional advising practices and automated, data-driven recommendation systems tailored to individual student backgrounds.