Designing Safe and Engaging AI Experiences for Children: Towards the Definition of Best Practices in UI/UX Design
Grazia Ragone, Paolo Buono, Rosa Lanzilotti
TL;DR
The paper addresses designing safe, engaging AI experiences for children and the challenge of measuring safety and trustworthiness in child-AI interactions. It advocates a holistic, stakeholder-driven framework that combines interdisciplinary collaboration, iterative design, rapid prototyping, and mixed-method evaluations to develop child-centered AI UI/UX. Concrete best practices (simplicity, transparency, caregiver-mediated customization, safety, and inclusion) are paired with a metrics-based evaluation framework grounded in Schneiderman's human-centered AI guidelines. The work aims to institutionalize responsible, ethical design practices within the CHI community and to advance learning-oriented, safer AI interactions for young users.
Abstract
This workshop proposal focuses on best practices in UI/UX design for AI applications aimed at children, emphasising safety, engagement, and ethics. It aims to address the challenge of measuring the safety, trustworthiness, and reliability of interactions between children and AI systems. Through collaborative discussions, participants will explore effective design strategies and ethical guidelines while developing methodologies for assessing the safety and reliability of AI interactions with children. This proposal seeks to foster responsible and child-centered AI design practices within the CHI community.