Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity

2026-02-15

AI Summary

This study addresses the enhancement of synergistic therapeutic effects between visual creation and dialogic interaction in art therapy. To this end, we introduce, for the first time, a multimodal large language model (MLLM) into the art therapy context, developing an AI chatbot capable of real-time analysis of users’ artwork while simultaneously engaging them in reflective dialogue. The work proposes a comprehensive AI-assisted design framework that integrates user profiling, dialogue depth and breadth, visual interaction, and risk management. Evaluation by five expert art therapists indicates that the system demonstrates strong potential as a therapeutic aid and provides clear directions for future refinement.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Interaction Techniques and Devices

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Therapeutic art activities, such as expressive drawing and painting, require the synergy between creative visual production and interactive dialogue. Recent advancements in Multimodal Large Language Models (MLLMs) have expanded the capacity of computing systems to interpret both textual and visual data, offering a new frontier for AI-mediated therapeutic support. This work-in-progress paper introduces an MLLM-powered chatbot that analyzes visual creation in real-time while engaging the creator in reflective conversations. We conducted an evaluation with five experts in art therapy and related fields, which demonstrated the chatbot's potential to facilitate therapeutic engagement, and highlighted several areas for future development, including entryways and risk management, bespoke alignment of user profile and therapeutic style, balancing conversational depth and width, and enriching visual interactivity. These themes provide a design roadmap for designing the future AI-mediated creative expression tools.

Problem

• therapeutic art
• multimodal chatbot
• AI-mediated support
• creative expression
• art therapy

Innovation

• Multimodal Large Language Models
• Therapeutic Art
• AI-mediated Therapy
• Real-time Visual Analysis
• Reflective Dialogue