Disclose with Care: Designing Privacy Controls in Interview Chatbots

2026-02-01

AI Summary

This study addresses the heightened risk of excessive personal information disclosure when users engage with chatbots on sensitive topics. To mitigate this privacy concern, the authors propose and evaluate two post-interaction privacy control mechanisms—free editing and AI-assisted editing—that enable users to revise conversation transcripts, thereby balancing privacy protection with data utility. The AI-assisted editing approach, a novel contribution, leverages natural language processing to automatically detect and suggest modifications to personally identifiable information (PII). In a controlled experiment with 188 participants, this method significantly reduced PII disclosure rates while preserving both data validity and user engagement experience, offering a practical solution for enhancing privacy in sensitive human–AI interactions.

Technology Category

• Machine Learning: Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Humans and AI: Interaction Techniques and Devices

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Privacy-enhancing technologies
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

Collecting data on sensitive topics remains challenging in HCI, as participants often withhold information due to privacy concerns and social desirability bias. While chatbots'perceived anonymity may reduce these barriers, research paradoxically suggests people tend to over-share personal or sensitive information with chatbots. In this work, we explore privacy controls in chatbot interviews to address this problem. The privacy control allows participants to revise their transcripts at the end of the interview, featuring two design variants: free editing and AI-aided editing. In a between-subjects study \red{($N=188$)}, we compared no-editing, free-editing, and AI-aided editing conditions in a chatbot-based interview on a sensitive topic. Our results confirm the prevalent issue of oversharing in chatbot-based interviews and show that AI-aided editing serves as an effective privacy-control mechanism, reducing PII disclosure while maintaining data quality and user engagement, thereby offering a promising approach to balancing ethical practice and data quality in such interviews.

Problem

• privacy controls
• chatbot interviews
• oversharing
• sensitive topics
• data quality

Innovation

• privacy control
• chatbot interviews
• AI-aided editing
• oversharing mitigation
• sensitive data collection