Search and Filter

Repository Feedback

Your feedback helps us improve the repository's content relevance and usability. Please share your thoughts to help us better serve researchers and practitioners.

Submit feedback

Submit a research study

Contribute to the repository:

Add a paper

Interaction With a Television Character Powered by Artificial Intelligence Promotes Children's Science Learning

Ying Xu, Julian Levine, Valery Vigil, Daniel Ritchie, Shan Zhang, Trisha Thomas, Carlos Barrera, Michelle Meza, Andres Sebastian Bustamante, Mark Warschauer
Date
Publisher
EdArXiv
Link
https://osf.io/preprints/edarxiv/m3ej9
Television and video programs are important educational resources for young children, especiallythosefromunder-resourcedhouseholds.Theseprogram potentialcanbeamplifiedif children are given the opportunity to meaningfully interact with media characters during their video watching. In this project, we partnered with PBS KIDS to develop interactive science- focused videos in which the main character, powered by artificial intelligence, engaged in conversation with children by asking them questions and providing responsive feedback. The children who watched the interactive video performed better in a science posttest compared to their peers who watched the non-interactive or pseudo-interactive videos. This paper sheds light on the feasibility and effectiveness of using conversational technologies to support children active learning from video watching.
Study at a glance
  • Question: Does interacting with an AI-powered TV character help children learn science from educational videos?
  • Setting and data: Children watching science-focused videos developed with PBS KIDS
  • Method: Compares science posttest scores of children watching AI-interactive videos with peers watching non-interactive or pseudo-interactive videos
Why it matters

Television and video programs are important educational resources for young children, especially those from under-resourced households. These programs' potential can be amplified if children are given the opportunity to meaningfully interact with media characters during video watching.

Key findings
  • Children watching interactive science videos with an AI character performed better on a science test than peers watching non-interactive or pseudo-interactive videos.
  • The AI-powered character successfully engaged children in conversations by asking them questions and providing responsive feedback during video programs.
  • Conversational technologies proved feasible and effective for supporting children's active learning during video watching.

Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.

What is the application?
Learning – Student Support
Who is the user?
Student
Who age?
Elementary (PK5)
Why use AI?
Outcomes – Other Academic
Study design
Impact – Randomized Controlled Trial