Wizard prompts that waited for delivery and a growing lexicon improved the robot's responsiveness over iterations¶

Claim · All claims
Evidence · 1 study · qualitative r2 · q2
Currency · newest study 2021 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Sending a prompt and waiting a sufficient time until it was delivered, plus a growing lexicon, improved the design. → Yanghee Kim 2021

Evidence¶

Yanghee Kim 2021¶

Yanghee Kim, Sherry Marx, Hung Viet Pham, Tung Nguyen. (2021). Designing for robot-mediated interaction among culturally and linguistically diverse children. Education Tech Research Dev. https://doi.org/10.1007/s11423-021-10051-2

q2 · i? · qualitative · r2

Qualitative analysis of recorded interaction sessions found that waiting after sending a prompt reduced interruptions; the authors add that as the team became more familiar with children's language and Skusie's lexicon grew, this aspect of the design improved.

"One important step toward a solution was for the human wizard to send a prompt and wait a sufficient time until the prompt was delivered to children and the children started to respond."

Discussion¶

Related Claims¶

• Flexible design with a human wizard anticipated kindergarteners' developing communication styles in robot-mediated interaction — related
• Reviews of classroom studies, read from their abstracts, associate longer teacher wait time with longer, higher-cognitive-level student responses, with no effect size recorded — related
• Iterative prompt refinement shifted a generative-AI tutor from tutorial-style explanation delivery toward dialogic Socratic support for K-12 beginners — related
• A communication robot as cooperative learning partner elicited student interactions similar to those with human partners — related