FeClustRE: Hierarchical Clustering and Semantic Tagging of App Features from User Reviews
Max Tiessler, Quim Motger
TL;DR
This paper tackles the challenge of extracting and organizing actionable app features from noisy user reviews for requirements engineering. It introduces FeClustRE, a hybrid pipeline that combines syntactic feature extraction (TransFeatEx) with an LLM-based classifier (T-FREX), followed by auto-tuned hierarchical clustering and LLM-driven semantic tagging to generate multi-level taxonomies stored in a graph database. Evaluations on expert and crowdsourced benchmarks show superior recall and balanced $F_\beta$ for the hybrid approach, with taxonomy labels aligning well with official app documentation and interpretability confirmed through qualitative analyses. The work provides an open-source framework enabling practitioners to prioritize features, compare apps, and perform market analysis using structured, semantically coherent feature taxonomies.
Abstract
[Context and motivation.] Extracting features from mobile app reviews is increasingly important for multiple requirements engineering (RE) tasks. However, existing methods struggle to turn noisy, ambiguous feedback into interpretable insights. [Question/problem.] Syntactic approaches lack semantic depth, while large language models (LLMs) often miss fine-grained features or fail to structure them coherently. In addition, existing methods output flat lists of features without semantic organization, limiting interpretation and comparability. Consequently, current feature extraction approaches do not provide structured, meaningful representations of app features. As a result, practitioners face fragmented information that hinder requirement analysis, prioritization, and cross-app comparison, among other use cases. [Principal ideas/results.] In this context, we propose FeClustRE, a framework integrating hybrid feature extraction, hierarchical clustering with auto-tuning and LLM-based semantic labelling. FeClustRE combines syntactic parsing with LLM enrichment, organizes features into clusters, and automatically generates meaningful taxonomy labels. We evaluate FeClustRE on public benchmarks for extraction correctness and on a sample study of generative AI assistant app reviews for clustering quality, semantic coherence, and interpretability. [Contribution.] Overall, FeClustRE delivers (1) a hybrid framework for feature extraction and taxonomy generation, (2) an auto-tuning mechanism with a comprehensive evaluation methodology, and (3) open-source and replicable implementation. These contributions bridge user feedback and feature understanding, enabling deeper insights into current and emerging requirements.