Security and Privacy Taxonomy Generation from Mobile App Reviews

2026-08-09

AI Summary

This study addresses the limitations of existing manually constructed taxonomies for security and privacy issues, which struggle to scale with the volume and dynamism of mobile app reviews. To overcome this challenge, the authors propose TaxoScale, a novel framework that integrates text filtering, recursive hierarchical clustering, and large language model–driven automated node labeling to enable dynamic expansion of taxonomies from massive review datasets. Evaluated across multiple dimensions—including path coherence, hierarchy depth, coverage breadth, and category novelty—TaxoScale significantly outperforms current automated taxonomy construction methods. The resulting taxonomy not only exhibits finer granularity and more comprehensive coverage of security and privacy concerns but also uncovers previously missing branches absent in prior classification schemes.

Abstract

Mobile app reviews are a rich, continuously renewing source of how users experience privacy and security, yet existing taxonomies of these concerns are hand-crafted and cannot keep pace with the evolving nature of the data. Automating taxonomy construction is the natural response, but scalability is the core challenge: current LLM- and clustering-based methods are developed for scientific corpora of a few thousand documents and do not extend to app review collections numbering in the hundreds of thousands. We address this gap in two ways. First, we filter app reviews for privacy- and security-related content, yielding a comprehensive corpus of over 600K reviews. Second, we introduce TaxoScale, a pipeline that handles taxonomy construction at this scale by extending an expert-defined taxonomy via Recursive Hierarchical Clustering and LLM-based node naming. TaxoScale outperforms strong automatic-taxonomy baselines on path, level, coverage, and novelty metrics, and discovers novel branches absent from prior taxonomies.

Problem

• security
• privacy
• taxonomy generation
• mobile app reviews
• scalability

Innovation

• TaxoScale
• Recursive Hierarchical Clustering
• LLM-based taxonomy construction
• scalable privacy taxonomy
• mobile app reviews