skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: Using Conversational Agents to Foster Young Children’s Science Learning from Screen Media
My dissertation project leverages an intelligent conversational agent embodied in an on-screen character to add social contingency into children’s science video watching experiences. This conversational agent has been developed in an iterative process and embedded in a new PBS KIDS science show, "Elinor Wonders Why." My research aims to understand the design, feasibility, and promise of virtual conversation with media characters in young children’s informal science learning through video watching.  more » « less
Award ID(s):
1906321
PAR ID:
10180778
Author(s) / Creator(s):
Date Published:
Journal Name:
Proceedings of the 19th ACM International Conference on Interaction Design and Children (IDC ’20)
Page Range / eLocation ID:
14-19
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Video programs are important, accessible educational resources for young children, especially those from an under-resourced backgrounds. These programs’ potential can be amplified if children are allowed to socially interact with media characters during their video watching. This paper presents the design and empirical investigation of interactive science-focused videos in which the main character, powered by a conversational agent, engaged in contingent conversation with children by asking children questions and providing responsive feedback. We found that children actively interacted with the media character in the conversational videos and their parents spontaneously provided support in the process. We also found that the children who watched the conversational video performed better in the immediate, episode-specific science assessment compared to their peers who watched the broadcast, non-interactive version of the same episode. Several design implications are discussed for using conversational technologies to better support child active learning and parent involvement in video watching. 
    more » « less
  2. Agency is essential to play. As we design conversational agents for early childhood, how might we increase the child-centeredness of our approaches? Giving children agency and control in choosing their agent representations might contribute to the overall playfulness of our designs. In this study with 33 children ages 4–5 years old, we engaged children in a creative storytelling interaction with conversational agents in stuffed animal embodiments. Young children conversed with the stuffed animal agents to tell stories about their creative play, engaging in question and answer conversation from 2 minutes to 24 minutes. We then interviewed the children about their perceptions of the agent’s voice, and their ideas for agent voices, dialogues, and interactions. From babies to robot daddies, we discover three themes from children’s suggestions: Family Voices, Robot Voices, and Character Voices. Additionally, children desire agents who (1) scaffold creative play in addition to storytelling, (2) foster personal, social, and emotional connections, and (3) support children’s agency and control. Across these themes, we recommend design strategies to support the overall playful child-centeredness of conversational agent design. 
    more » « less
  3. Informal science learning sites (ISLS) create opportunities for children to learn about science outside of the classroom. This study analyzed children’s learning behaviors in ISLS using video recordings of family visits to a zoo, children’s museum, or aquarium. Furthermore, parent behaviors, features of the exhibits and the presence of an educator were also examined in relation to children’s behaviors. Participants included 63 children (60.3% female) and 44 parents in 31 family groups. Results showed that parents’ science questions and explanations were positively related to children observing the exhibit. Parents’ science explanations were also negatively related to children’s science explanations. Furthermore, children were more likely to provide science explanations when the exhibit was not interactive. Lastly there were no differences in children’s behaviors based on whether an educator was present at the exhibit. This study provides further evidence that children’s interactions with others and their environment are important for children’s learning behaviors. 
    more » « less
  4. Research in both laboratory and museum settings suggests that children’s exploration and caregiver–child interaction relate to children’s learning and engagement. Most of this work, however, takes a third-person perspective on children’s exploration of a single activity or exhibit, and does not consider children’s perspectives on their own exploration. In contrast, the current study recruited 6-to 10-year-olds (N = 52) to wear GoPro cameras, which recorded their first-person perspectives as they explored a dinosaur exhibition in a natural history museum. During a 10-min period, children were allowed to interact with 34 different exhibits, their caregivers and families, and museum staff however they wished. Following their exploration, children were asked to reflect on their exploration while watching the video they created and to report on whether they had learned anything. Children were rated as more engaged when they explored collaboratively with their caregivers. Children were more likely to report that they learned something when they were more engaged, and when they spent more time at exhibits that presented information didactically rather than being interactive. These results suggest that static exhibits have an important role to play in fostering learning experiences in museums, potentially because such exhibits allow for more caregiver–child interaction. 
    more » « less
  5. Early literacy skills are crucial predictors of children’s academic success. Dialogic reading—an interactive approach where adults and children engage in discussions about stories—has proven highly effective in developing these skills. However, many families face barriers implementing this practice due to time constraints, limited resources, or linguistic challenges. We present StoryPal, an LLM-powered conversational agent that facilitates dialogic reading through contextual questioning, adaptive scaffolding, and personalized feedback. In a study with 23 children ages 4-7 from diverse socioeconomic and linguistic backgrounds, we found high levels of verbal engagement with distinct patterns between English-dominant and bilingual children. The system’s dynamic scaffolding effectively supported struggling readers while challenging proficient ones. Parents valued StoryPal as a supplementary tool that maintained children’s reading engagement when they were unavailable, but emphasized that it should not replace parent-child interactions. Our findings demonstrate the potential of LLM-powered agents to support dialogic reading by adhering to established educational practices. 
    more » « less