Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity

Le Lin; Zihao Zhu; Rainbow Tin Hung Ho; Jing Liao; Yuhan Luo

doi:10.1145/3802974.3809425

Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity

Le Lin
, Zihao Zhu
, Rainbow Tin Hung Ho
, Jing Liao^*
, Yuhan Luo

^*Corresponding author for this work

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Downloads (CityUHK Scholars)

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.

© 2026 Copyright held by the owner/author(s)

Original language	English
Title of host publication	DIS '26
Subtitle of host publication	Proceedings of the 2026 Designing Interactive Systems Conference
Editors	Ching Chiuan Yen, Jung-Joo Lee, Ellen Yi-Luen Do, Clement Zheng, Daisy Yoo, Tony Tang
Place of Publication	United States
Publisher	Association for Computing Machinery
Pages	253-258
ISBN (Electronic)	979-8-4007-2563-0
DOIs	https://doi.org/10.1145/3802974.3809425
Publication status	Published - 12 Jun 2026
Event	ACM Designing Interactive Systems 2026 (DIS 2026) - National University of Singapore, Singapore Duration: 13 Jun 2026 → 17 Jun 2026 https://dis.acm.org/2026/

Conference

Conference	ACM Designing Interactive Systems 2026 (DIS 2026)
Abbreviated title	ACM DIS 2026
Place	Singapore
Period	13/06/26 → 17/06/26
Internet address	https://dis.acm.org/2026/

Funding

We thank our participants for their time and interests. This project was supported by the Innovation and Technology Fund (ITF) of the Innovation and Technology Commission (ITC) of the Hong Kong Special Administrative Region (HKSAR) Government (# ITS/269/24FP) and City University of Hong Kong (# 7020106).

Research Keywords

Therapeutic art
Image understanding
Chatbot customization
Human-AI collaboration
Multimodel agent

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

10.1145/3802974.3809425

495901369.pdfFinal Published version, 4.06 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Lin, L., Zhu, Z., Ho, R. T. H., Liao, J., & Luo, Y. (2026). Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity. In C. C. Yen, J.-J. Lee, E. Y.-L. Do, C. Zheng, D. Yoo, & T. Tang (Eds.), DIS '26: Proceedings of the 2026 Designing Interactive Systems Conference (pp. 253-258). Association for Computing Machinery. https://doi.org/10.1145/3802974.3809425

Lin, Le ; Zhu, Zihao ; Ho, Rainbow Tin Hung et al. / Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity. DIS '26: Proceedings of the 2026 Designing Interactive Systems Conference. editor / Ching Chiuan Yen ; Jung-Joo Lee ; Ellen Yi-Luen Do ; Clement Zheng ; Daisy Yoo ; Tony Tang. United States : Association for Computing Machinery, 2026. pp. 253-258

@inproceedings{8c290d6f34444590a0218629c6d52e83,

title = "Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity",

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{\textquoteright}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. {\textcopyright} 2026 Copyright held by the owner/author(s)",

keywords = "Therapeutic art, Image understanding, Chatbot customization, Human-AI collaboration, Multimodel agent",

author = "Le Lin and Zihao Zhu and Ho, \{Rainbow Tin Hung\} and Jing Liao and Yuhan Luo",

year = "2026",

month = jun,

day = "12",

doi = "10.1145/3802974.3809425",

language = "English",

pages = "253--258",

editor = "Yen, \{Ching Chiuan\} and Jung-Joo Lee and Do, \{Ellen Yi-Luen\} and Clement Zheng and Daisy Yoo and Tony Tang",

booktitle = "DIS '26",

publisher = "Association for Computing Machinery",

address = "United States",

note = "ACM Designing Interactive Systems 2026 (DIS 2026), ACM DIS 2026 ; Conference date: 13-06-2026 Through 17-06-2026",

url = "https://dis.acm.org/2026/",

}

Lin, L , Zhu, Z, Ho, RTH, Liao, J & Luo, Y 2026, Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity. in CC Yen, J-J Lee, EY-L Do, C Zheng, D Yoo & T Tang (eds), DIS '26: Proceedings of the 2026 Designing Interactive Systems Conference. Association for Computing Machinery, United States, pp. 253-258, ACM Designing Interactive Systems 2026 (DIS 2026), Singapore, 13/06/26. https://doi.org/10.1145/3802974.3809425

Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity. / Lin, Le ; Zhu, Zihao; Ho, Rainbow Tin Hung et al.
DIS '26: Proceedings of the 2026 Designing Interactive Systems Conference. ed. / Ching Chiuan Yen; Jung-Joo Lee; Ellen Yi-Luen Do; Clement Zheng; Daisy Yoo; Tony Tang. United States: Association for Computing Machinery, 2026. p. 253-258.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity

AU - Lin, Le

AU - Zhu, Zihao

AU - Ho, Rainbow Tin Hung

AU - Liao, Jing

AU - Luo, Yuhan

PY - 2026/6/12

Y1 - 2026/6/12

N2 - 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. © 2026 Copyright held by the owner/author(s)

AB - 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. © 2026 Copyright held by the owner/author(s)

KW - Therapeutic art

KW - Image understanding

KW - Chatbot customization

KW - Human-AI collaboration

KW - Multimodel agent

UR - https://www.scopus.com/pages/publications/105042623480

UR - https://www.scopus.com/pages/publications/105042623480#tab=impact

U2 - 10.1145/3802974.3809425

DO - 10.1145/3802974.3809425

M3 - RGC 32 - Refereed conference paper (with host publication)

SP - 253

EP - 258

BT - DIS '26

A2 - Yen, Ching Chiuan

A2 - Lee, Jung-Joo

A2 - Do, Ellen Yi-Luen

A2 - Zheng, Clement

A2 - Yoo, Daisy

A2 - Tang, Tony

PB - Association for Computing Machinery

CY - United States

T2 - ACM Designing Interactive Systems 2026 (DIS 2026)

Y2 - 13 June 2026 through 17 June 2026

ER -

Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity

Abstract

Conference

Funding

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

ITF: Next-Generation Product Placement: Combining CG and AI Technologies for Intelligent Advertising

Cite this

Exploring a Multimodal Chatbot as a Facilitator in Therapeutic Art Activity

Abstract

Conference

Funding

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

ITF: Next-Generation Product Placement: Combining CG and AI Technologies for Intelligent Advertising

Cite this