An Empathy-Based Sandbox Approach to Bridge the Privacy Gap among Attitudes, Goals, Knowledge, and Behaviors

TL;DR

This paper presents an empathy-based sandbox environment that uses AI-generated personas to help users understand privacy implications, aiming to bridge the gap between privacy attitudes and behaviors.

Contribution

It introduces a novel pipeline for generating realistic personas using large language models and demonstrates how this approach fosters empathy and improves privacy literacy.

Findings

Generated personas are of adequate quality.

Users show cognitive and emotional empathy.

Privacy-related applications are affected by different personas.

Abstract

Managing privacy to reach privacy goals is challenging, as evidenced by the privacy attitude-behavior gap. Mitigating this discrepancy requires solutions that account for both system opaqueness and users' hesitations in testing different privacy settings due to fears of unintended data exposure. We introduce an empathy-based approach that allows users to experience how privacy attributes may alter system outcomes in a risk-free sandbox environment from the perspective of artificially generated personas. To generate realistic personas, we introduce a novel pipeline that augments the outputs of large language models (e.g., GPT-4) using few-shot learning, contextualization, and chain of thoughts. Our empirical studies demonstrated the adequate quality of generated personas and highlighted the changes in privacy-related applications (e.g., online advertising) caused by different personas. Furthermore, users demonstrated cognitive and emotional empathy towards the personas when interacting with our sandbox. We offered design implications for downstream applications in improving user privacy literacy.