Large Language Models to Support Learning Through Storytelling
Our goal is to investigate the influence of large language models and generative AI on children’s education. As a first step, we’ve begun a research study that employs generative AI to jointly create math-oriented narratives with children. In this interactive process, both the children and the AI alternately contribute to the story, with the AI fostering an environment where children utilize their mathematical knowledge and linguistic skills to guide the story’s character on their journey.
Conversational Agents as Reading Partners
To enrich children’s home literacy environments, this project investigates the potential for using conversational agents to support children’s language learning by engaging them in storybook reading. Grounded in the framework of dialogic reading, I have designed, developed, and tested fully automated smart speaker reading partners that narrate stories to children while engaging them in relevant, open-ended conversation. As an extension of this project, I will develop and research culturally-relevant conversational e-books in collaboration with Sesame Workshop to support parent-child interactions among Latino families.
Conversational Technologies for Supporting STEM Discourse
In this project, I am partnering with PBS KIDS to integrate conversational agents into children’s STEM television shows so that children can have contingent interaction with media characters, with the goal of supporting active engagement and learning. The end goal of this project is to distribute the conversational videos as publicly accessible content via PBS KIDS platforms to millions of children across the country.
Scalable Conversational AI for Literacy Development
The overall objective of this project is to evaluate the feasibility of using automatic question-answer generation to facilitate the learning and assessment of narrative comprehension skills, a critical component of reading proficiency. This innovation can enable large-scale, cost-effective development and production of learning and assessment resources. This project involves 1) creating a high-quality benchmark dataset of dialogic reading questions, 2) developing models to automatically generate questions from stories, and 3) building an integrated system that provides children with interactive reading experiences.
Explainable AI and Trust
This series of studies aims to understand the psychological and social consequences of AI transparency. I examine whether providing children and adults with information about how AI works affects their trust and parasocial relationships towards AI. Eventually, these studies will inform the development of curriculum to promote children’s AI literacy, which is crucial to help them use these technologies effectively and become less vulnerable to misinformation and bias.
Media Usage in Multicultural Families
I am partnering with PBS SoCal to co-design a series of math-focused video programs accompanied by hands-on learning activities (e.g., crafting, art projects) that situate math learning within the cultural resources of a local Latino community, investigating how drawing on diverse groups’ “funds of knowledge” can promote parent-child joint STEM engagement. This research will provide critical evidence on a culturally responsive, media-enriched approach to early STEM learning that builds on the assets of marginalized communities.
Digital Reading in Early Childhood
This line of research focuses on how the design of interactive touchscreen storybooks supports or hinders children’s language learning. I examine the effectiveness of common design features (e.g., hotspots, audio narration) and identify developmentally appropriate techniques to improve the usability of e-book interface. I have also analyzed children’s e-reading behaviors through mining log data.