PACEE: Supporting Children's Personal Emotion Education through Parent-AI Collaboration

TL;DR

<3-5 sentence high-level summary>

Abstract

Emotion education is a crucial lesson for children aged 3 to 6. However, existing technologies primarily focus on promoting emotion education from the child's perspective, often neglecting the central role of parents in guiding early childhood emotion development at home. In this work, we conducted co-design sessions with five experienced kindergarten teachers and five parents to identify parental challenges and the roles that AI can play in family emotion education. Guided by these insights, we developed PACEE, an assistant for supporting parent-AI collaborative emotion education. PACEE enables parents to engage in conversations about common emotional scenarios, with multiple forms of AI support to address parents' challenges. It combines insights from parents and AI to model children's emotional states and delivers personalized, parent-mediated guidance. In a user study involving 16 families, we found that PACEE significantly enhances parent-child engagement, encourages more in-depth emotional communication, and improves the parental experience. Our findings advance emotion coaching guidelines for family education in the era of generative AI, offering valuable insights for designing AI-supported, parent-centered family education systems.

Figures (13)

• Figure 1: Our 3-phased study procedure.
• Figure 2: Photos taken in the formative studies, including: (a) the setup of an observational experiment, where parents guide their children following a predefined script, and (b) a conceptual design image presented during the interview session to illustrate our design objectives.
• Figure 3: Main screens of PACEE. PACEE consists of 3 modules: (a) Parent-Child Adventure Game. Each adventure game facilitates parent-guided emotional conversations centered on a specific emotional scenario, promoting meaningful interactions between parents and children. (b) Parental Feedback Report, which provides feedback on the adventure game and practical recommendations for parents. (c) Child Emotional Modeling collaborates with parents to develop a child's emotional profile. Parents contribute long-term observational data about their child, gathered through interactions with an AI interviewer.
• Figure 4: Mechanism of PACEE modeling children's emotional profiles collaboratively with parents. It functions in two scenarios: (1) individual parent interviews conducted by an AI Interviewer and (2) AI-facilitated parent-child emotion conversations monitored by a Conversation Agent. The Cognitive Analyzer processes inputs from both scenarios, analyzing and synthesizing emotional profile data. The resulting Child's Emotional Profile includes three sub-dimensions: emotion understanding, emotion expression, and emotion regulation. Additionally, it compares the parent's understanding of the child's emotions with conversational analysis by the AI, offering a nuanced perspective on the child's emotional development.
• Figure 5: Agent workflow of PACEE.