Table of Contents
Fetching ...

AnimAlte:Designing AI-Infused Cartoon Videos to Improve Preschoolers' Language Learning with Family Engagement at Home

Shiya Tsang, Ruiyao Miao, Junren Xiao, Hui Xiong

TL;DR

The paper addresses the lack of AI-enhanced support for vocabulary learning through cartoons by introducing AnimAlte, an AI-infused system that engages preschoolers and families via four learning phases: real-time Q&A, active vocabulary review, real-world associations, and contextual expansion. It leverages multimodal AI components (visual-language models, large language models, and image generation) to create an interactive, personalized learning flow that connects cartoon content to real life and extended language use. A formative study with parents and experts identifies four key design challenges, which informs the AnimAlte design, and a remote pilot with five families demonstrates positive reception, improved engagement, and enhanced family collaboration. Overall, the work provides architectural, interaction, and design guidelines for future AI-powered educational video systems aimed at at-home language development for early learners.

Abstract

Cartoon videos have proven to be effective in learning vocabulary to preschool children.However, we have little knowledge about integrating AI into cartoon videos to provide systematic, multimodal vocabulary learning support. This late-breaking work present \name{}, an AI-powered cartoon video system that enables real-time Q\&A, vocabulary review, and contextual learning. Preliminary findings contextualized how families interact with \name{} to support vocabulary learning. Parents appreciated the system for its personalized, engaging experiences, fostering collaboration, and encouraging self-reflection on parenting. This study offers valuable design implications for informing future video systems to support vocabulary learning.

AnimAlte:Designing AI-Infused Cartoon Videos to Improve Preschoolers' Language Learning with Family Engagement at Home

TL;DR

The paper addresses the lack of AI-enhanced support for vocabulary learning through cartoons by introducing AnimAlte, an AI-infused system that engages preschoolers and families via four learning phases: real-time Q&A, active vocabulary review, real-world associations, and contextual expansion. It leverages multimodal AI components (visual-language models, large language models, and image generation) to create an interactive, personalized learning flow that connects cartoon content to real life and extended language use. A formative study with parents and experts identifies four key design challenges, which informs the AnimAlte design, and a remote pilot with five families demonstrates positive reception, improved engagement, and enhanced family collaboration. Overall, the work provides architectural, interaction, and design guidelines for future AI-powered educational video systems aimed at at-home language development for early learners.

Abstract

Cartoon videos have proven to be effective in learning vocabulary to preschool children.However, we have little knowledge about integrating AI into cartoon videos to provide systematic, multimodal vocabulary learning support. This late-breaking work present \name{}, an AI-powered cartoon video system that enables real-time Q\&A, vocabulary review, and contextual learning. Preliminary findings contextualized how families interact with \name{} to support vocabulary learning. Parents appreciated the system for its personalized, engaging experiences, fostering collaboration, and encouraging self-reflection on parenting. This study offers valuable design implications for informing future video systems to support vocabulary learning.

Paper Structure

This paper contains 20 sections, 2 figures, 2 tables.

Figures (2)

  • Figure 1: User interface flow of AnimAlte (A), episode navigation (B), cartoon watching and question answering (C), review (D), real-world association (E), and contextual expansion (F).
  • Figure 2: : Overview of AnimAlte system architecture.