Explorations in AI and Creative Learning New Tools to Expand How Young People Imagine, Create, and Tinker with Scratch

Abstract

As generative AI tools become increasingly prevalent in young people’s lives, these technologies have a growing influence over the way that children learn. While much of the early work at the intersection of AI and education has focused on the development of intelligent tutoring systems designed to deliver content more efficiently, this thesis explores how generative AI might be used to support the creative learning process by sparking curiosity, encouraging exploration, and helping young people express themselves creatively. In this thesis, I explore ways of integrating generative AI with Scratch, the world's largest programming community for children, while remaining aligned with the core values of Scratch: creativity, playfulness, and self-expression. I designed three tools that extend the Scratch ecosystem: Scratch Connect, which explores using generative AI to help Scratchers discover projects that inspire them to create while opening the black box of recommendation systems; scrAItch, which investigates how people can iterate with generative AI by using text-based inputs to create and tinker with Scratch projects; and Scratch Spark, which reimagines the new learner experience by using generative AI to help users create personally meaningful “spark projects.” This thesis describes the process of imagining, creating, and reflecting on these tools, including many of the challenges and tensions that we encountered along the way. I discuss observations and feedback from creative workshops with young people, and conclude by reflecting on open questions and opportunities for future work in designing generative AI tools that support creative learning.