From Framework to Practice: Youth Negotiations of Privacy with Smart Voice Assistants Through the PEA-AI Lens

Abstract

Smart voice assistants (SVAs) have become embedded in the daily lives of youth, introducing complex privacy challenges due to always-on listening, shared device usage, and opaque data practices. This study applies the Privacy-Ethics Alignment in AI (PEA-AI) framework to examine how youth perceive and negotiate privacy within SVAs. Through a survey of 469 Canadian youth (aged 16-24), we measured five privacy constructs: Perceived Privacy Risk (PPR), Perceived Privacy Benefits (PPBf), Algorithmic Transparency and Trust (ATT), Privacy Self-Efficacy (PSE), and Privacy-Protective Behavior (PPB). Results reveal a persistent privacy paradox. While youth express moderate to high privacy concerns (PPR M = 3.61), perceived benefits (PPBf M = 3.00) and protective actions (PPB M = 3.03) remain moderate, with transparency and trust scoring lowest (ATT M = 2.52). Heavy SVA users report higher benefits and lower risk perception than light users. High protective behavior is strongly associated with both high risk perception and high self-efficacy. Qualitative insights from prior focus groups contextualize these patterns, illustrating how youth navigate tensions between convenience, control, and trust. The findings provide actionable design principles for SVA along with implications for multi-stakeholder governance and youth-centered digital literacy.