eaSEL: Promoting Social-Emotional Learning and Parent-Child Interaction through AI-Mediated Content Consumption

TL;DR

This paper introduces eaSEL, an AI-driven system that embeds social-emotional learning (SEL) into children's video consumption by generating in-context reflection activities and post-viewing parent–child conversation prompts without requiring co-viewing. It presents a pipelined LLM-based approach (transcription via Whisper; detection and generation via GPT-4) to identify SEL moments, create child-centered activities, and craft parent prompts, validated through a technical evaluation and a mixed-methods study with 20 parent–child dyads. Findings show that eaSEL boosts children’s emotion-word usage in retellings and supports meaningful parent–child discussions, while also highlighting challenges in social reasoning tasks, vocabulary suitability, and content safety for independent use. The work demonstrates the potential of AI to enhance at-home SEL practice and family engagement with digital media, and outlines safety, personalization, and real-world deployment directions for broader impact.

Abstract

As children increasingly consume media on devices, parents look for ways this usage can support learning and growth, especially in domains like social-emotional learning. We introduce eaSEL, a system that (a) integrates social-emotional learning (SEL) curricula into children's video consumption by generating reflection activities and (b) facilitates parent-child discussions around digital media without requiring co-consumption of videos. We present a technical evaluation of our system's ability to detect social-emotional moments within a transcript and to generate high-quality SEL-based activities for both children and parents. Through a user study with N=20 parent-child dyads, we find that after completing an eaSEL activity, children reflect more on the emotional content of videos. Furthermore, parents find that the tool promotes meaningful active engagement and could scaffold deeper conversations around content. Our work paves directions in how AI can support children's social-emotional reflection of media and family connections in the digital age.

Figures (7)

• Figure 1: Example app flow for the child user. The interaction starts when children (a) select a video, (b) watch a video, then (c) select an activity. The child is first reminded of the moment where the social-emotional skill occurred in the show (d) and then they complete the activity (e). Finally, the child verbally explains the artifact they created if the activity did not involve audio recording (f).
• Figure 2: Example parent interface showing a summary of the show, the social emotional skill detected, the child's activity playback, and generated conversation starters.
• Figure 3: Overview of pipelined prompting approach, with inputs and example outputs.
• Figure 4: Human evaluation of GPT-4 generated child-focused SEL activities, with five annotators for each of the 59 generated child activities.
• Figure 5: Human evaluation of GPT-4 generated parent-child conversation starters.