🧠 AI Ed Wiki

📄 Research Article

AI-Driven Tools for Enhancing Campus Well-being: Prevention and Intervention

◐ medium · 2026-05-16higher-ed, llm, generative-ai, student-experience, affective-computing, edtech-platform, administrator, ai-literacy

AI-Driven Campus Well-being Tools

Synthesis

This dissertation presents an integrated AI framework for campus well-being spanning prevention (improving feedback collection) and intervention (advancing mental health detection). It represents an important application of LLM and Generative AI technologies to Student Experience that extends beyond academic learning to holistic student support in Higher Ed.

On the prevention side, TigerGPT — a personalized survey chatbot grounded in conversational design and engagement theory — achieved 75% usability and 81% satisfaction, demonstrating that AI-mediated feedback collection can improve on traditional survey instruments. AURA, an adaptive follow-up question framework using reinforcement learning, dynamically selects question types (validate, specify, reflect, probe) to deepen responses, achieving a +0.12 mean quality gain (p=0.044, d=0.66).

On the intervention side, PsychoGPT provides explainable mental health assessment built on DSM-5 and PHQ-8 guidelines — a Affective Computing application that prioritizes clinical grounding and interpretability over black-box classification. The Stacked Multi-Model Reasoning (SMMR) architecture reduces hallucination risk by layering expert models: early layers handle localized subtasks while later layers reconcile findings, outperforming single-model solutions on the DAIC-WOZ benchmark.

The integrated framework — where adaptive survey insights flow into specialized mental health detection models — represents a novel Edtech Platform architecture for campus well-being. For the Administrator perspective, this work provides a concrete roadmap for universities seeking to deploy AI tools that monitor student satisfaction and detect mental health risks — areas where many institutions currently lack effective methods.

Connected Concepts

  • LLM
  • Generative AI
  • Student Experience
  • Higher Ed
  • Affective Computing
  • Edtech Platform
  • Administrator

    • Connected Articles

  • Bloom Aligned Educational Control Llms — From Execution to Education: A Bloom-Aligned Framework for Measuring Educational Control in LLMs
  • LLM Sentiment Analysis Education Research — LLM-assisted sentiment analysis for integrated computational and qualitative mixed methods education research: A case study of students' written reflection assignments
  • AI Learning Assistants Higher Ed Large Scale — Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
  • AI Generated Feedback Higher Ed — Artificial intelligence and feedback in university education: effectiveness and student perceptions
  • Youtube Frames Chatgpt Education — How YouTube Frames ChatGPT Use in Education: An Epistemic Network Analysis with Supporting Multimodal Metadata
  • Multi Site VR Immersive Learning — Design and Implementation of a Real-time Multi-site Immersive Learning System Using Photon Fusion

    • Citation

    Tang, J. (2026). New AI-Driven Tools for Enhancing Campus Well-being: A Prevention and Intervention Approach [PhD Dissertation, University of Missouri]. arXiv:2605.10804.