PACEE: Parent-Centered AI Scaffolding for Emotion Education in Early Childhood Conversations
Year: 2026
Type: conference-paper
Abstract: Emotion education is critical for children aged 3 to 6. However, existing technologies depend substantially on direct child-AI interaction, overlooking the central role of parents in guiding early emotional development at home. To address this gap, we conducted co-design sessions with five kindergarten teachers and five parents to identify key parental challenges and opportunities for AI support in family emotion education. Based on these insights, we developed PACEE, an LLM-based assistant designed around an asymmetric triadic interaction framework: AI primarily supports parents while preserving parent-child interaction. PACEE provides parent-centered AI scaffolding that supports parents in real-time conversation through personalized guidance, post-hoc reflection through trackable feedback, and understanding children’s emotional states through modeling. We evaluated PACEE with 16 families. Results showed that PACEE increased parent-child conversational engagement and improved parents’ overall experience when guiding emotion-related conversations. Together, we contribute an asymmetric triadic interaction framework for AI-supported family education, offering design insights for AI systems that support parents while preserving parent-led parent–child interaction.
Authors: Yu Mei, Xutong Wang, Ziyao Zhang, Yiming Fu, Shiyi Wang, Qingyang Wan, Qinghuan Lan, Chang Liu, Jie Cai, Chun Yu, Yuanchun Shi
Institutions: Tsinghua University, Dublin City University
Language: English
Subfield: Education
Field: Social Sciences
Domain: Social Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W7106116172