用AI工具提升校园心理健康监测，兼顾反馈收集与早期干预。
New AI-Driven Tools for Enhancing Campus Well-being: A Prevention and Intervention Approach
- 开发聊天机器人TigerGPT和AURA框架，提升问卷互动质量与深度。
- AURA使提问更智能，响应质量提升12%，重复提问减少63%。
- PsychoGPT结合临床指南，实现可解释的抑郁风险初筛，减少幻觉。
校园心理健康影响学业表现，但多数高校缺乏有效的满意度监测与心理风险识别手段。本文提出预防（改进反馈收集）与干预（推进心理状态检测）相结合的整合框架。预防方面，构建基于大模型的个性化调查聊天机器人TigerGPT，融合对话设计与参与理论，用户可用性达75%，满意度达81%。为克服其重复性与响应深度不足，引入强化学习框架AURA，根据96次历史对话初始化，动态调整后续提问类型（验证、细化、反思、探查），使用LSDE质量信号（长度、自我披露、情绪、具体性）评估，实现平均质量提升0.12（p=0.044, d=0.66），指定类提示减少63%，验证行为增加10倍。干预方面，研究表达性叙事故事（ENS）在心理筛查中的作用，发现BERT(128)可在无关键词情况下捕捉细微语言特征，而传统分类器依赖明确心理术语。进一步开发基于DSM-5与PHQ-8指南的PsychoGPT，实现初始压力分级、症状打分及外部评分一致性校验，具备可解释性。为降低幻觉，提出堆叠多模型推理（SMMR），分层处理局部任务并最终整合结果，在DAIC-WOZ数据集上优于单模型方案，准确率、F1与PHQ-8评分均更优。最终框架实现从动态问卷到专用心理检测模型的闭环联动。
原文摘要 · Abstract (English)
Campus well-being underpins academic success, yet many universities lack effective methods for monitoring satisfaction and detecting mental health risks. This dissertation addresses these gaps through prevention (improving feedback collection) and intervention (advancing mental health detection), unified under an integrated framework. For prevention, we developed TigerGPT, a personalized survey chatbot leveraging LLMs to engage users in context-aware conversations grounded in conversational design and engagement theory, achieving 75% usability and 81% satisfaction. To address its limitations in repetitiveness and response depth, we introduced AURA, a reinforcement-learning framework that adapts follow-up question types (validate, specify, reflect, probe) within a session using an LSDE quality signal (Length, Self-disclosure, Emotion, Specificity), initialized from 96 prior conversations. AURA achieved +0.12 mean quality gain (p=0.044, d=0.66), with 63% fewer specification prompts and 10x more validation behavior. For intervention, we examine Expressive Narrative Stories (ENS) for mental health screening, showing BERT(128) captures nuanced linguistic features without keyword cues, while conventional classifiers depend heavily on explicit mental health terms. We then developed PsychoGPT, an LLM built on DSM-5 and PHQ-8 guidelines that performs initial distress classification, symptom-level scoring, and reconciliation with external ratings for explainable assessment. To reduce hallucinations, we proposed Stacked Multi-Model Reasoning (SMMR), layering expert models where early layers handle localized subtasks and later layers reconcile findings, outperforming single-model solutions on DAIC-WOZ in accuracy, F1, and PHQ-8 scoring. Finally, a cohesive framework unifies these tools, enabling adaptive survey insights to flow directly into specialized mental health detection models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。