Noel: A Chatbot Persona to Support Children Designing for Others

Designing for others encourages children to empathize with and consider different perspectives and needs. A chatbot persona could allow children to design for stakeholder groups that are challenging to involve directly in educational activities, such as people with disabilities. In this paper, we explore how an artificial intelligence chatbot persona leveraging the GPT-4 large language model can support children’s design empathy while designing for others. We report the design, development process, and implementation of a chatbot persona representing a 12-year-old child with low vision named Noel. The exploratory case study consisted of three 90- to 120-minute workshop sessions with nineteen students (ages 11 to 13) in a grade 6/7 classroom. Results illustrate ways that Noel supported students throughout the design process, their expressions of design empathy, and their experiences. We present implications for developers and educators along with future directions for research.