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

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.

• The paper demonstrates an AI system that detects social-emotional learning events in video transcripts and generates child-appropriate reflection activities.
• The methodology employs GPT-4 for SEL detection, supported by human validators to ensure clear and age-appropriate language.
• User studies with parent-child dyads revealed increased emotion vocabulary in children and improved family conversations after media consumption.

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

The paper "eaSEL: Promoting Social-Emotional Learning and Parent-Child Interaction through AI-Mediated Content Consumption," authored by Shen et al., presents an innovative approach to augment children's social-emotional learning (SEL) through technology. The system, eaSEL, is designed to integrate SEL curricula into children's video consumption via AI-driven reflection activities and conversation prompts, fostering independent and joint family engagement in media settings. This research combines AI methodologies, human-computer interaction (HCI), and psychological theories to address critical barriers in current digital learning environments and SEL applications.

Technical Implementation and Evaluation

The core of eaSEL is a system that utilizes LLMs to detect SEL-related events within video transcripts, subsequently generating child-appropriate reflection activities aligned with these events. This system uniquely positions itself in the digital learning landscape by offering an AI-mediated reflection mechanism that functions independently from traditional co-viewing or parent-involved learning models.

1. SEL Detection and Activity Generation: The system employs a pipelined approach using OpenAI's GPT-4 model to conduct SEL detection tasks and generate related activities. The technical evaluation section underscores the capability of LLMs in effectively identifying SEL events and generating relevant educational content, though noting occasional challenges in language simplification for young audiences.
2. Human Validator Input: The study engaged multiple human evaluators to confirm the system's accuracy in detecting SEL skills and generating age-appropriate content for children. The results demonstrated high performance, with a noted need for enhancement in child-friendly language and thematic content safety measures.

User Study Outcomes

The study includes a mixed-methods user evaluation with 20 parent-child dyads to understand the effectiveness and receptivity of eaSEL’s approach:

• Children's Engagement: The system's activities led to increased usage of emotion-related vocabulary among children, suggesting enhanced engagement with SEL content post-activity.
• Parental Insight and Involvement: Parents valued the system's capability to foster deeper child engagement and appreciated the potential to scaffold enhanced family conversations. There was an expressed interest in implementing the system in everyday use, with the acknowledgment that it could significantly aid in practicing SEL skills actively.

Implications for AI and SEL Integration

The research makes several significant contributions to the fields of educational technology, AI, and SEL by:

• Independent Learning Context Adaptation: The system offers a novel approach to independent educational engagement, reducing reliance on parental involvement during media consumption yet still promoting active learning.
• Technology-Mediated Family Interactions: By facilitating reflective discussions without necessitating co-viewing, eaSEL supports dynamic parent-child interaction post-content consumption, offering flexible engagement opportunities for parents.
• Future Directions: The study paves avenues for future advancements in AI-enhanced educational technologies. It highlights potential interdisciplinary research intersections, specifically focusing on developing personalized models tuned for child-friendliness and cultural sensitivity. Moreover, this research suggests further exploration into refining systems to balance autonomous operation with personalized educational interventions.

In summary, the paper distinctly showcases the effectiveness of AI in addressing gaps within traditional SEL educational approaches and proposes a scalable framework for implementing SEL across diverse digital media platforms. The integration of AI to facilitate SEL signifies a forward-thinking approach conducive to enriching children’s development in contemporary media-rich environments.