PIs: Cynthia Breazeal, Massachusetts Institute of Technology (Award Details)
Stephanie Gottwald, Tufts University (Award Details)

Early language ability, including vocabulary skills and oral language knowledge during preschool, is an important predictor of children’s academic success in subsequent school years. Social robots that can engage children as personalized learning companions hold great promise in augmenting the learning experience of children with parents and teachers. The ultimate goal is to foster the development, learning and promotion of academic achievements and the well-being of children. Such robots offer unique opportunities of guided, personalized and controlled social interaction during the delivery of a desired curriculum. They can play, learn and engage with children in the real world — physically, socially and emotively. This research project is developing and evaluating an autonomous personalized social robot tutor-companion that can engage preschool children in storytelling activities during a long-term interaction. The research goal is to assess the impact that such an interaction may have on children’s language skills development. The project advances the fields of autonomous storytelling generation and analysis, as well as the interaction between autonomous social robots and preschool children to promote learning. Its broader impact is to develop an effective technology that augments the preschool setting that promotes children’s language development in a personalized and socially engaging way.

This research project develops and assesses the efficacy of an autonomous, personalized social robot that engages as a learning companion on the language development of pre-school children in the context of storytelling tasks. For this purpose, the research project develops a novel automatic story analysis tool, and a new personalized story generation algorithm, that pushes the envelope of current understanding of free-form storytelling and how fosters the development of early language skills in pre-school aged children. Additionally, the research develops of a fully autonomous social robot that interacts with preschool children in the real-life environment of a preschool. A 9-month longitudinal study at multiple preschool sites is carried out to evaluate the impact of long-term interaction with the storytelling robot on children’s engagement and language skill development. The research aims to increase the current understanding of the impact of longitudinal interaction with social robot on children’s language development. Ultimately, this can inspire new tools and practices for early pre-literacy and language education (as well as other domains such as STEM) in the home, classroom, and beyond.