Scholarlink

This paper examines how Virtual Reality (VR) and Generative AI (GenAI) can address the growing mental health crisis among students when traditional support systems are overwhelmed. VR creates immersive therapeutic environments for exposure therapy and stress management, while GenAI enables personalized, adaptive interactions. The review covers five application areas: VR exposure therapy for anxiety, VR-based stress regulation and mindfulness, AI-driven personalization, VR social skills training, and AI-generated therapeutic content. Early evidence shows promise for scalable, engaging interventions beyond traditional clinical settings. However, significant limitations exist: small studies, short follow-up periods, inconsistent measurements, and unresolved ethical concerns around privacy, bias, and safety. The authors propose a framework with four components—Sensing, Inference, Adaptation, and Evaluation (SIAE)—to guide ethical development and call for rigorous research, transparency, and interdisciplinary collaboration before widespread implementation.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptive Mental Health Interventions: Integrating VR and Generative AI in Learning Environments

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Attilio Della Greca,
  • Ilaria Amaro,
  • Paola Barra

摘要

This paper examines how Virtual Reality (VR) and Generative AI (GenAI) can address the growing mental health crisis among students when traditional support systems are overwhelmed. VR creates immersive therapeutic environments for exposure therapy and stress management, while GenAI enables personalized, adaptive interactions. The review covers five application areas: VR exposure therapy for anxiety, VR-based stress regulation and mindfulness, AI-driven personalization, VR social skills training, and AI-generated therapeutic content. Early evidence shows promise for scalable, engaging interventions beyond traditional clinical settings. However, significant limitations exist: small studies, short follow-up periods, inconsistent measurements, and unresolved ethical concerns around privacy, bias, and safety. The authors propose a framework with four components—Sensing, Inference, Adaptation, and Evaluation (SIAE)—to guide ethical development and call for rigorous research, transparency, and interdisciplinary collaboration before widespread implementation.