Through the Looking Glass: LLM-Based Analysis of AR/VR Android Applications Privacy Policies
Abdulaziz Alghamdi, David Mohaisen
TL;DR
This paper investigates AR/VR privacy policies using a BERT-based analysis to assess clarity and completeness, benchmarking against free and premium websites. It introduces xr-scope, a pipeline for collecting 302 AR/VR policies, processing text, mapping segments to nine privacy categories, and performing BERT-based classification to identify positive and highlighted content. Results show AR/VR policies are more transparent than free content but still lag behind premium sites, with strong emphasis on core privacy practices like data sharing and retention. The study demonstrates high BERT performance, substantial policy detail, and category-specific trends, offering practical guidance for policy-tool development and regulatory alignment in AR/VR privacy practices.
Abstract
\begin{abstract} This paper comprehensively analyzes privacy policies in AR/VR applications, leveraging BERT, a state-of-the-art text classification model, to evaluate the clarity and thoroughness of these policies. By comparing the privacy policies of AR/VR applications with those of free and premium websites, this study provides a broad perspective on the current state of privacy practices within the AR/VR industry. Our findings indicate that AR/VR applications generally offer a higher percentage of positive segments than free content but lower than premium websites. The analysis of highlighted segments and words revealed that AR/VR applications strategically emphasize critical privacy practices and key terms. This enhances privacy policies' clarity and effectiveness.