Featured Projects
Incorporating a Bilingual Conversational Agent for Co-reading with Latine Families
In partnership with the Joan Ganz Cooney Center at Sesame Workshop, we created a bilingual conversational agent featuring Rosita from Sesame Street, coupled with a story reading interface, Rosita Reads with My Family.
The primary objectives of this project are to 1) create an interactive learning environment for children with active dialogue throughout the reading experience, 2) encourage parental participation and family discussion with conversational prompts that connect the storybook plot to family life, and 3) create a culturally-sound, shared reading experience for Latine families with our conversational agent's bilingual features and relevant storybook content.
The primary objectives of this project are to 1) create an interactive learning environment for children with active dialogue throughout the reading experience, 2) encourage parental participation and family discussion with conversational prompts that connect the storybook plot to family life, and 3) create a culturally-sound, shared reading experience for Latine families with our conversational agent's bilingual features and relevant storybook content.
Promoting Children's Science Learning: Interactions with an Artificially Intelligent TV Character
In collaboration with PBS KIDS, we created interactive science video programs featuring Elinor from Elinor Wonders Why, driven by a conversational agent. This character engages children in dialogue by posing questions about the episode and delivering contingent feedback. In the course of our investigation, I have administered episodes and assessments to 100 children for our data analyses of children's acquisition of scientific concepts with AI-assisted TV interactions.
Publications
Xu, Y., He, K., Vigil, V., Ojeda-Ramirez, S., Liu, X., Levine, J., Cervera, K., Warschauer, M. (2023, June). “Rosita Reads With My Family”: Developing A Bilingual Conversational Agent to Support Parent-Child Shared Reading. https://doi.org/10.1145/3585088.3589354 (Best Paper Award)