Research

Built on Research.
Designed for Young Learners.

For more than six years, our team has studied how dialogic AI — technology designed to engage children in meaningful back-and-forth conversation — can support early learning. Instead of simply presenting information, conversational agents can act as interactive reading partners: asking questions, responding to children's answers, and encouraging children to explain their thinking.

6+
Years of Research
5
Partner Institutions

Our Approach

Why Conversation Matters

Children learn through conversation.

Dialogic reading is an interactive approach to shared reading that engages children in back-and-forth conversation about a story. A reading partner asks questions, listens to children's responses, and provides feedback based on what they say.

AI as an Interactive Reading Partner

More than listening or reading.

Conversational agents create opportunities for children to do more than simply listen or read a story.

Within The Science Adventures of Luna & Leo, these conversational moments are designed to reinforce science concepts and vocabulary while encouraging children to actively engage with what they are learning.

Our Findings

Past Research

Promising results for dialogic AI.

Our previous research has found promising results for the use of dialogic AI with young children.

What's Next

Bringing this work into classrooms.

We are now bringing this work into TK–K classrooms to better understand how bilingual, interactive science e-books can support science learning and complement teachers' existing instructional practices.

Publications

2025
  • He, K., Cervera, K., Levine, J., Xu, Y., Collins, P., & Warschauer, M. (2025). Promoting parent-child shared reading with a bilingual conversational agent. International Journal of Human-Computer Studies, 199. https://doi.org/10.1016/j.ijhcs.2025.103489
2024
  • Xu, Y., He, K., Levine, J., Ritchie, D., Pan, Z., Bustamante, A., & Warschauer, M. (2024). Artificial intelligence enhances children’s science learning from television shows. Journal of Educational Psychology. https://dx.doi.org/10.1037/edu0000889
  • He, K., Levine, J., Cervera, K., Ojeda-Ramirez, S., Xu, Y., & Warschauer, M. (2024, May). A home study of parent-child co-reading with a bilingual conversational agent. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (pp. 1–8). https://doi.org/10.1145/3613905.3650836
2023
  • Xu, Y., Vigil, V., Ritchie, D., Zhang, S., Thomas, T., Barrera, C., Meza, M., Bustamante, A. S., & Warschauer, M. (2023). Interaction with a television character powered by artificial intelligence promotes children’s science learning. Annual Meeting of the American Educational Research Association.
  • Xu, Y. (2023). Talking with machines: Can conversational technologies serve as children's social partners? Child Development Perspectives, 17(1), 53–58.
  • Xu, Y., He, K., Vigil, V., Ojeda-Ramirez, S., Liu, X., Levine, J., Cervera, K., & Warschauer, M. (2023). “Rosita Reads With My Family”: Developing a bilingual conversational agent to support parent-child shared reading. In Proceedings of the ACM International Conference on Interaction Design and Children (IDC ’23). Association for Computing Machinery. https://doi.org/10.1145/3585088.3589354
2022
  • Yao, B., Wang, D., Wu, T., Zhang, Z., Li, T. J.-J., Yu, M., & Xu, Y. (2022). It is AI's turn to ask humans a question: Question-answer pair generation for children’s story books (arXiv:2109.03423). arXiv. http://arxiv.org/abs/2109.03423
  • Xu, Y., Vigil, V., Bustamante, A., & Warschauer, M. (2022). Contingent interaction with a television character promotes children's science learning and engagement. Journal of Applied Developmental Psychology. https://doi.org/10.1016/j.appdev.2022.101439
  • Xu, Y., Wang, D., Yu, M., Ritchie, D., Yao, B., Wu, T., Zhang, Z., Li, T., Bradford, N., Sun, B., Hoang, T., Sang, Y., Hou, Y., Ma, X., Yang, D., Peng, N., Yu, Z., & Warschauer, M. (2022). Fantastic questions and where to find them: FairytaleQA — An authentic dataset for narrative comprehension. Association for Computational Linguistics. https://arxiv.org/abs/2203.13947
  • Xu, Y., Vigil, V., Bustamante, A., & Warschauer, M. (2022). “Elinor's talking to me!”: Integrating conversational AI into children's science narrative programming. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems.
2020
  • Xu, Y., & Warschauer, M. (2020). Exploring young children’s engagement in joint reading with a conversational agent. Proceedings of the Interaction Design and Children Conference, 216–228. https://doi.org/10.1145/3392063.3394417