Date of Defense
4-5-2026 3:00 PM
Location
E1-3057
Document Type
Thesis Defense
Degree Name
Master of Science in Information Technology Management
College
College of Information Technology
Department
Information Technology
First Advisor
Saed Alrabaee
Keywords
Student well-being, Conversational AI, Sentiment analysis, Stress detection, Natural language processing, Personalized learning support
Abstract
Over the past few years, academic stress and the issue of mental well-being of students has become a pressing issue in the context of educational settings, influencing academic achievements and the general quality of life to a considerable extent. There is a growing use of digital platforms by students as a source of academic support, but most of the solutions available do not support the emotional state of the users or offer any other personalized and context-sensitive support. To address this difficulty, this paper introduces the design and development of a stress-aware conversational support system of students using advanced natural language processing methods and large language models. The main goal of the study is to explore the possibility of an LLM-based conversation AI, using sentiment analysis and stress-level detection algorithms, to effectively detect the emotional condition of students and provide an individual academic assistance and well-being advice. The system proposed will classify messages by the student based on structured sentiment classification to identify stress levels as neutral, mild stress, or high stress, and combine mood check-ins and conversation history into a composite stress scoring model. The system responds dynamically to the computed stress level by adjusting responses, study recommendations, focus techniques, and resource referrals. The pre-trained large language model is used as a methodology to leverage contextual. content generation, personalization by rules, content moderation, and risk monitoring systems to maintain safety and ethics. Simulated student interactions were used to test the system to identify that it can properly detect. stress levels and give right and individualized recommendations. The results suggest that the proposed system can be helpful in distinguishing various. signs of stress in students and provide context-specific and valuable feedback, which highlights the potential of the system to increase student engagement, well-being, and academic. productivity. The major contribution of this study is the introduction of a exhaustive, conversational framework that is stress sensitive that fills the gap between academic assistance. and emotional support. Through the combination of sentiment analysis, personalization, and risk. escalation plans, this research paper will help in the development of safer, more adaptive, and learning support systems that are student-focused.
Included in
AI Powered Student Support and Development Platform
E1-3057
Over the past few years, academic stress and the issue of mental well-being of students has become a pressing issue in the context of educational settings, influencing academic achievements and the general quality of life to a considerable extent. There is a growing use of digital platforms by students as a source of academic support, but most of the solutions available do not support the emotional state of the users or offer any other personalized and context-sensitive support. To address this difficulty, this paper introduces the design and development of a stress-aware conversational support system of students using advanced natural language processing methods and large language models. The main goal of the study is to explore the possibility of an LLM-based conversation AI, using sentiment analysis and stress-level detection algorithms, to effectively detect the emotional condition of students and provide an individual academic assistance and well-being advice. The system proposed will classify messages by the student based on structured sentiment classification to identify stress levels as neutral, mild stress, or high stress, and combine mood check-ins and conversation history into a composite stress scoring model. The system responds dynamically to the computed stress level by adjusting responses, study recommendations, focus techniques, and resource referrals. The pre-trained large language model is used as a methodology to leverage contextual. content generation, personalization by rules, content moderation, and risk monitoring systems to maintain safety and ethics. Simulated student interactions were used to test the system to identify that it can properly detect. stress levels and give right and individualized recommendations. The results suggest that the proposed system can be helpful in distinguishing various. signs of stress in students and provide context-specific and valuable feedback, which highlights the potential of the system to increase student engagement, well-being, and academic. productivity. The major contribution of this study is the introduction of a exhaustive, conversational framework that is stress sensitive that fills the gap between academic assistance. and emotional support. Through the combination of sentiment analysis, personalization, and risk. escalation plans, this research paper will help in the development of safer, more adaptive, and learning support systems that are student-focused.