Ying Xu, Ph.D.

Assistant Professor
Graduate School of Education
Harvard University

Children reading picture books in different settings

Storybook reading by family members provides a stimulating environment for children’s development of their language and communication skills. The benefits of storybook reading are amplified by engaging children in dialogic interactions that revolve around story narratives. By increasing opportunities for dialogic reading, we can ensure that more children develop the language and literacy skills necessary for school success.

We have carried out a series of studies to design and investigate the impact of conversational agents in the form of smart speakers to support children’s language learning by engaging them in storybook reading, with a particular focus on children from multilingual backgrounds.

Funding Sources

NSF: Advancing Latino Children’s Science Learning through Community Co-Design of AI-Enhanced Bilingual E-Books (2024-2028)

Highlights

  • Having dialogue with an agent reading partner promoted children’s story comprehension and engagement equally as well as a human reading partner did (paper in Child Development).

  • Children’s communication patterns differed when they interacted with a human vs. agent:

    • The agent partner promoted the audible intelligibility of children’s responses
    • Reading with a human partner elicited longer, more lexically diverse, and more relevant responses from children (paper in Computers & Education).

  • Children had varying patterns of communicating with the agents based on their age and language proficiency (paper in IDC2020).

  • This series of studies has produced practical design principles that inform the development of conversational technologies for young users who are still developing their language skills and cognitive functioning (paper in CHI2021; paper in IDC2020).

  • When designed properly, conversational AI can promote parent-children interaction during shared story reading, allowing me to examine the benefits of “trialogue” among an agent, parent, and the child for language development (paper in IDC 2023).

  • Teachers and parents are generally enthusiastic about using AI to support joint reading activities at home and at school (paper in IDC 2023).

Upcoming Studies

  • Can AI-assisted science eBooks support children’s language development and science learning?
    • We are conducting co-design studies with Latine communities in California and Michigan to develop a series of 24 science-focused storybooks for families with children aged 4 to 6.
    • We will test the effects of access to these culturally responsive storybooks on children’s English and home language development, science learning, and attitudes toward heritage languages and cultures.
  • Can AI support parents in developing awareness and strategies to support children’s language and science learning at home?
    • We are developing AI-assisted interventions aimed at helping parents build effective reading routines—such as asking open-ended questions, encouraging story retelling, and providing feedback during shared book reading.
    • Our focus is on designing systems that follow a gradual transfer of responsibility model, where AI initially models and scaffolds the interaction, but parents gradually take the lead over time.
    • We are preparing to conduct a home-based RCT to examine the feasibility and impact of this approach on parental engagement and children’s language development.

Selected Publications

  • He, K., Cervera, K., Levine, J., Xu, Y., Collins, P., Warschauer, M. (2025). Promoting parent-child shared reading with a bilingual conversational agent. In International Journal of Human-Computer Studies. [DOI]

  • 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, New York, NY, USA. [DOI]

  • Xu, Y., Aubele, J., Vigil, V., Bustamante, A., Kim, Y-S., & Warschauer, M. (2022). Dialogue with a conversational agent promotes children’s story comprehension via enhanced engagement. Child Development. [DOI]

  • Xu, Y., Wang, D., Collins, P., Lee, H., & Warschauer, M. (2021). Same benefits, different communication patterns: Comparing children’s reading with a conversational agent vs. a human partner. Computers & Education. 161. 104059. [DOI]

  • Xu, Y., Branham, S., Collins, P., Deng, X., Warschauer, M. (2021). Are current voice interfaces designed to support children’s language development? In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. [DOI]

  • Xu, Y., & Warschauer, M. (2020). Exploring young children’s engagement in joint reading with a conversational agent. In Proceedings of the 19th ACM International Conference on Interaction Design and Children (IDC ’20). Association for Computing Machinery, New York, NY, USA. [DOI]

  • Xu, Y., & Warschauer, M. (2020). A content analysis of voice-based apps on the market for early literacy development. In Proceedings of the 19th ACM International Conference on Interaction Design and Children (IDC ’20). Association for Computing Machinery, New York, NY, USA. [DOI] (Best Paper Award Honorable Mention)

  • Xu, Y., & Warschauer, M. (2019). Young children’s reading and learning with conversational agents. In CHI Conference on Human Factors in Computing Systems Extended Abstracts. May 4–9, 2019, Glasgow, Scotland, UK. ACM. [DOI]

Updated: