Child-AI Creativity Support Tools: A Co-Design Study with Children
thesis
posted on 2024-12-01, 00:00authored byFrancesca Fusco
Creativity Support Tools (CSTs) such as child-AI visual storytelling where children can verbally narrate and figuratively draw their stories are increasingly used to scaffold and support children’s creative expression, helping them overcome blocks such as the fourth-grade slump. However, these child-AI visual storytelling interfaces are not always designed to with children’s mental models and expectations in mind and accommodate their developing cognitive and motor skills which could impact the way the interface understands children’s natural speech or drawing inputs.
The goal of this MS thesis is to understand children’s mental models of child-AI visual storytelling tools, especially in regards to interaction methods and level of automation support needed from AI to support children’s creative storytelling expression. To answer our questions, we conducted four co-design sessions at UW’s Kids Team with 20 children aged 5-12. The sessions were hybrid and lasted 90 minutes each. The sessions aimed to elicit insights on the following matters related to children's creativity tools: interaction, feedback, error reaction, and technical and conceptual automation. We are currently in the process of analyzing our data using a qualitative thematic analysis approach to elicit conceptual models of children’s expectations of child-AI visual storytelling interfaces.
Our conceptual model will inform the designers of future creativity interfaces for children so that their needs are taken into account in the development of creativity support tools. Additionally, we aim to share guidelines for conducting design sessions with children that endorse their engagement and provide researchers with useful outputs.