Examining the Effect of Explanations of AI Privacy Redaction in AI-mediated Interactions

TL;DR

This study explores how explanations of privacy redactions in AI-mediated communication influence user trust, revealing that detailed explanations improve perceived effectiveness and trust, especially with extensive redactions and considering individual differences.

Contribution

The paper introduces a user study demonstrating that explanations of redaction operations enhance trust and effectiveness perceptions in AI-mediated privacy-sensitive communication.

Findings

Explanations increase perceived privacy preservation effectiveness.

Contextual redaction extent influences reliance on explanations.

Individual differences affect explanation preferences and trust.

Abstract

AI-mediated communication is increasingly being utilized to help facilitate interactions; however, in privacy sensitive domains, an AI mediator has the additional challenge of considering how to preserve privacy. In these contexts, a mediator may redact or withhold information, raising questions about how users perceive these interventions and whether explanations of system behavior can improve trust. In this work, we investigate how explanations of redaction operations can affect user trust in AI-mediated communication. We devise a scenario where a validated system removes sensitive content from messages and generates explanations of varying detail to communicate its decisions to recipients. We then conduct a user study with $180$ participants that studies how user trust and preferences vary for cases with different amounts of redacted content and different levels of explanation detail. Our results show that participants believed our system was more effective at preserving privacy when explanations were provided ($p<0.05$, Cohen's $d \approx 0.3$). We also found that contextual factors had an impact; participants relied more on explanations and found them more helpful when the system performed extensive redactions ($p<0.05$, Cohen's $f \approx 0.2$). We also found that explanation preferences depended on individual differences as well, and factors such as age and baseline familiarity with AI affected user trust in our system. These findings highlight the importance and challenge of balancing transparency and privacy in AI-mediated communications and suggest that adaptive, context-aware explanations are essential for designing privacy-aware, trustworthy AI systems.