Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TaleBot: A Tangible AI Companion to Support Children in Co-creative Storytelling for Resilience Cultivation

Yonglin Chen, Jingjing Zhang, Kezhuo Wang, Pengcheng An, Xueliang Li

TL;DR

TaleBot, an AI-empowered system that supports children to co-create stories about overcoming everyday adversities tailored to their personal situations, is designed with design implications for using generative AI to support children's mental health education and interventions across school and family contexts.

Abstract

Resilience is a key factor affecting children's mental wellbeing and future development. Yet, limited HCI research has explored how to help children build resilience through adversarial experiences. Informed by a formative study with elementary school teachers and professional psychologists, we design TaleBot, an AI-empowered system that supports children to co-create stories about overcoming everyday adversities tailored to their personal situations. We evaluated the system with 12 elementary children in school counseling rooms under teacher guidance and conducted reflective interviews with parents upon the Child-AI co-created stories. The findings show that TaleBot encourages children in self-expression of feelings and thoughts, creating opportunities for teachers to provide personalized support and for parents to better understand the profound impact of family communication on children's mental wellbeing. We conclude with design implications for using generative AI to support children's mental health education and interventions across school and family contexts.

TaleBot: A Tangible AI Companion to Support Children in Co-creative Storytelling for Resilience Cultivation

TL;DR

TaleBot, an AI-empowered system that supports children to co-create stories about overcoming everyday adversities tailored to their personal situations, is designed with design implications for using generative AI to support children's mental health education and interventions across school and family contexts.

Abstract

Resilience is a key factor affecting children's mental wellbeing and future development. Yet, limited HCI research has explored how to help children build resilience through adversarial experiences. Informed by a formative study with elementary school teachers and professional psychologists, we design TaleBot, an AI-empowered system that supports children to co-create stories about overcoming everyday adversities tailored to their personal situations. We evaluated the system with 12 elementary children in school counseling rooms under teacher guidance and conducted reflective interviews with parents upon the Child-AI co-created stories. The findings show that TaleBot encourages children in self-expression of feelings and thoughts, creating opportunities for teachers to provide personalized support and for parents to better understand the profound impact of family communication on children's mental wellbeing. We conclude with design implications for using generative AI to support children's mental health education and interventions across school and family contexts.
Paper Structure (48 sections, 15 figures, 3 tables)

This paper contains 48 sections, 15 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Resilience Building through Everyday Adversities for Children
  4. Digital and AI-empowered Mental Health for Children in HCI
  5. AI-empowered Storytelling Systems
  6. Formative Study
  7. Method
  8. Key Findings
  9. KF1: Children face diverse family and school adversities.
  10. KF2: Appropriate Support to help children elaborate their feelings and thoughts.
  11. KF3: The Dual Nature of Adversity and Support for Post-adversarial Growth
  12. KF4: Barriers and Limitations in Current Support Systems
  13. KF5: Child-centered Design with Open-ended Interfaces for Adults' Participation
  14. Design Requirements
  15. Designing TaleBot
  16. ...and 33 more sections

Figures (15)

  • Figure 1: The TaleBot interface (left) and three primary interaction modes (right).
  • Figure 2: The expert-facing interface allows expert to customize personalized storylines for child-AI interactions. Panel (a) shows the outline list that can load data and distribute content to the child-facing interface. Panel (b) displays chapter previews and branching options. Panel (c) shows a story outline customized for participant C1, where Chapter 3 contains two branches: (c)a leads to a positive storyline, while (c)b leads to a negative storyline. Panel (d) demonstrates that when users click on a chapter in the preview panel, they can edit setting descriptions and plot details, or use AI assistance for modifications.
  • Figure 3: The inputs, outputs, and workflows of seven agents.
  • Figure 4: The figure illustrates the study setup in a school counseling room: (a) the teacher (school counselor) (left) guided the children (right) in co-creating a story with TaleBot placed on the table of the counseling room, and (b) the child interacted with TaleBot in the arms.
  • Figure 5: Study procedure.
  • ...and 10 more figures