Embodied Empathy: A Multimodal AR and LLM-Powered System for Self-Attachment Psychotherapy with Self-Initiated Humour
2026-08-03 • Human-Computer Interaction
Human-Computer InteractionMultimedia
AI summaryⓘ
The authors developed a new mobile app to help people with their mental health by combining a special humor technique and self-attachment therapy. The app uses customizable 3D childhood avatars, augmented reality, and a virtual therapist powered by a language model to reflect users' emotions. In an eight-day study with 16 people, the app was found to be doable and helped improve moods. Personal avatars and talking features helped users feel more connected, and emotion mirroring kept users engaged when it worked well. The authors also noticed that users want chatbots to be more active in guiding conversations rather than just reacting.
Self-Initiated Humour Protocol (SIHP)Self-Attachment Technique (SAT)3D avatarsAugmented Reality (AR)Large Language Models (LLM)Emotion mirroringVirtual therapistDigital mental healthUser engagementConversational AI
Authors
Xinyan Ye, Gwyneth Phang, Anandha Gopalan, Abbas Edalat
Abstract
The growing global demand for mental health support increasingly exceeds the supply of qualified practitioners, creating an urgent need for scalable digital interventions that can deliver meaningful emotional connection. In response, we present a novel multimodal application that operationalises the Self-Initiated Humour Protocol (SIHP) within a Self-Attachment Technique (SAT) framework. Our mobile application integrates customisable 3D childhood avatars, augmented reality, and an LLM-driven virtual therapist capable of automated emotion mirroring. An eight-day user study (N=16) indicates the system's feasibility and improvements in self-reported mood. Results show that personalised avatars and text-to-speech output strengthen emotional bonding and perceived empathy. Although emotion mirroring boosts engagement, its effectiveness depends heavily on classification accuracy and animation intensity. Moreover, findings indicate a shift in user expectations--from reactive chatbots to proactive conversational facilitators. We conclude with design implications for leveraging AI and AR to cultivate embodied empathy in digital mental health tools.