Date
Publisher
arXiv
Advances in artificial intelligence have facilitated the use of large
language models (LLMs) and AI-generated synthetic media in education, which may
inspire HCI researchers to develop technologies, in particular, embodied
conversational agents (ECAs) to simulate the kind of scaffolding children might
receive from a human partner. In this paper, we will propose a design prototype
of a peer-like ECA named STARie that integrates multiple AI models - GPT-3,
Speech Synthesis (Real-time Voice Cloning), VOCA (Voice Operated Character
Animation), and FLAME (Faces Learned with an Articulated Model and Expressions)
that aims to support narrative production in collaborative storytelling,
specifically for children aged 4-8. However, designing a child-centered ECA
raises concerns about age appropriateness, children privacy, gender choices of
ECAs, and the uncanny valley effect. Thus, this paper will also discuss
considerations and ethical concerns that must be taken into account when
designing such an ECA. This proposal offers insights into the potential use of
AI-generated synthetic media in child-centered AI design and how peer-like AI
embodiment may support children\textquotesingle s storytelling.
Study at a glance
- Question: How can an animated AI companion be designed to support storytelling for young children?
- Setting and data: Not stated in the abstract
- Method: Design prototype proposal and discussion of design and ethical considerations
Why it matters
While embodied conversational agents can simulate human scaffolding to support children's storytelling, designing child-centered agents raises concerns about age appropriateness, children's privacy, gender choices, and the uncanny valley effect.
Key findings
- For children aged 4–8, an animated peer-like conversational agent combining text, voice, and facial AI may support collaborative storytelling.
- Developing conversational tools for young children raises key concerns regarding privacy, age appropriateness, character gender, and unsettling, unnatural appearances.
- Synthetic media and language models allow virtual characters to simulate the collaborative support children receive from a human partner.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
