Investigating User Perspectives on Differentially Private Text Privatization
Preprint
Abstract
Recent literature has seen a considerable uptick in $\textit{Differentially Private Natural Language Processing}$ (DP NLP). This includes DP text privatization, where potentially sensitive input texts are transformed under DP to achieve privatized output texts that ideally mask sensitive information $\textit{and}$ maintain original semantics. Despite continued work to address the open challenges in DP text privatization, there remains a scarcity of work addressing user perceptions of this technology, a crucial aspect which serves as the final barrier to practical adoption. In this work, we conduct a survey study with 721 laypersons around the globe, investigating how the factors of $\textit{scenario}$, $\textit{data sensitivity}$, $\textit{mechanism type}$, and $\textit{reason for data collection}$ impact user preferences for text privatization. We learn that while all these factors play a role in influencing privacy decisions, users are highly sensitive to the utility and coherence of the private output texts. Our findings highlight the socio-technical factors that must be considered in the study of DP NLP, opening the door to further user-based investigations going forward.
Keywords
All Related Versions
This publication has 49 references indexed in Scilit:
- TEM: High Utility Metric Differential Privacy on Text2023
- Towards Effective Differential Privacy Communication for Users’ Data Sharing Decision and Comprehension2020
- Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text2019
- Generalised Differential Privacy for Text Document Processing2019
- SynTF2018
- Vignette methodologies for studying clinicians’ decision-making: Validity, utility, and application in ICD-11 field studiesInternational Journal of Clinical and Health Psychology, 2015
- Experimental Vignette Studies in Survey ResearchMethodology, 2010
- An analysis of variance test for normality (complete samples)Biometrika, 1965
- Multiple Comparisons Using Rank SumsTechnometrics, 1964
- Use of Ranks in One-Criterion Variance AnalysisJournal of the American Statistical Association, 1952