YouthCare: Building a Personalized Collaborative Video Censorship Tool to Support Parent-Child Joint Media Engagement

TL;DR

This work tackles the challenge of reducing teen exposure to risky online videos while alleviating parental mediation burden in Joint Media Engagement (JME). It introduces YouthCare, a three-module system built on Multimodal Large Language Models that enables collaborative configuration, explainable censorship, and feedback reporting to support parent–child decision-making. A formative study with teenagers and parents informs design goals, and a subsequent evaluation with 10 pairs demonstrates high acceptance and actionable insights for refining collaborative JME tools. The work offers design guidelines and highlights challenges around human–AI balance, indirect/direct communication, and privacy in future parent–child JME systems.

Abstract

To mitigate the negative impacts of online videos on teenagers, existing research and platforms have implemented various parental mediation mechanisms, such as Parent-Child Joint Media Engagement (JME). However, JME generally relies heavily on parents' time, knowledge, and experience. To fill this gap, we aim to design an automatic tool to help parents/children censor videos more effectively and efficiently in JME. For this goal, we first conducted a formative study to identify the needs and expectations of teenagers and parents for such a system. Based on the findings, we designed YouthCare, a personalized collaborative video censorship tool that supports parents and children to collaboratively filter out inappropriate content and select appropriate content in JME. An evaluation with 10 parent-child pairs demonstrated YouthCare's several strengths in supporting video censorship, while also highlighting some potential problems. These findings inspire us to propose several insights for the future design of parent-child collaborative JME systems.

Figures (15)

• Figure 1: The framework of YouthCare.
• Figure 2: Preference configuration process.
• Figure 3: Consensus-building process (illustrating an example where a teenager first provides their preference panel).
• Figure 4: Personalized Video Censorship Module and Feedback Report Module.
• Figure 5: Get initial preference panel (the interface is translated from Chinese for clarity).