FeClustRE: Hierarchical Clustering and Semantic Tagging of App Features from User Reviews

• URL: http://arxiv.org/abs/2510.18799v1
• Date: Tue, 21 Oct 2025 16:54:21 GMT
• Title: FeClustRE: Hierarchical Clustering and Semantic Tagging of App Features from User Reviews
• Authors: Max Tiessler, Quim Motger,
• Abstract summary: FeClustRE is a framework integrating hybrid feature extraction, hierarchical clustering with auto-tuning and semantic labelling.<n>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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Turning Semantics into Topology: LLM-Driven Attribute Augmentation for Collaborative Filtering [27.20519975467197]
  Topology-Augmented Graph Collaborative Filtering (TAGCF) is a novel framework that transforms semantic knowledge into topological connectivity.<n>To effectively model the heterogeneous relations in this augmented structure, we propose Adaptive Relation-weighted Graph Convolution.
  arXiv  Detail & Related papers  (2026-02-24T17:01:47Z)
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression [55.51959317490934]
  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding.<n>We argue that graphs inherently contain rich structural and semantic information, and that their effective exploitation can unlock potential gains in LLMs reasoning performance.<n>We propose Homophily-aware Structural and Semantic Compression for LLMs (HS2C), a framework centered on exploiting graph homophily.
  arXiv  Detail & Related papers  (2026-01-13T03:35:18Z)
• CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning [67.18702329644526]
  CoT Referring enhances model reasoning across modalities through a structured, chain-of-thought training data structure.<n>We restructure the training data to enforce a new output form, providing new annotations for existing datasets.<n>We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance.
  arXiv  Detail & Related papers  (2025-10-03T08:50:21Z)
• Question-Driven Analysis and Synthesis: Building Interpretable Thematic Trees with LLMs for Text Clustering and Controllable Generation [1.3750624267664158]
  We introduce Recursive Thematic Partitioning (RTP) to interactively build a binary tree.<n>Each node in the tree is a natural language question that semantically partitions the data, resulting in a fully interpretable taxonomy.<n>We show that RTP's question-driven hierarchy is more interpretable than the keyword-based topics from a strong baseline like BERTopic.
  arXiv  Detail & Related papers  (2025-09-26T11:27:22Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• SCAN: Structured Capability Assessment and Navigation for LLMs [54.54085382131134]
  textbfSCAN (Structured Capability Assessment and Navigation) is a practical framework that enables detailed characterization of Large Language Models.<n>SCAN incorporates four key components:.<n>TaxBuilder, which extracts capability-indicating tags from queries to construct a hierarchical taxonomy;.<n>RealMix, a query synthesis and filtering mechanism that ensures sufficient evaluation data for each capability tag;.<n>A PC$2$-based (Pre-Comparison-derived Criteria) LLM-as-a-Judge approach achieves significantly higher accuracy compared to classic LLM-as-a-Judge method
  arXiv  Detail & Related papers  (2025-05-10T16:52:40Z)
• GUM-SAGE: A Novel Dataset and Approach for Graded Entity Salience Prediction [12.172254885579706]
  Graded entity salience assigns entities scores that reflect their relative importance in a text.<n>We introduce a novel approach for graded entity salience that combines the strengths of both approaches.<n>Our approach shows stronger correlation with scores based on human summaries and alignments, and outperforms existing techniques.
  arXiv  Detail & Related papers  (2025-04-15T01:26:14Z)
• CLEAR-KGQA: Clarification-Enhanced Ambiguity Resolution for Knowledge Graph Question Answering [13.624962763072899]
  KGQA systems typically assume user queries are unambiguous, which is an assumption that rarely holds in real-world applications.<n>We propose a novel framework that dynamically handles both entity ambiguity (e.g., distinguishing between entities with similar names) and intent ambiguity (e.g., clarifying different interpretations of user queries) through interactive clarification.
  arXiv  Detail & Related papers  (2025-04-13T17:34:35Z)
• Localizing Factual Inconsistencies in Attributable Text Generation [74.11403803488643]
  We introduce QASemConsistency, a new formalism for localizing factual inconsistencies in attributable text generation.<n>We show that QASemConsistency yields factual consistency scores that correlate well with human judgments.
  arXiv  Detail & Related papers  (2024-10-09T22:53:48Z)
• Hierarchical Indexing for Retrieval-Augmented Opinion Summarization [60.5923941324953]
  We propose a method for unsupervised abstractive opinion summarization that combines the attributability and scalability of extractive approaches with the coherence and fluency of Large Language Models (LLMs) Our method, HIRO, learns an index structure that maps sentences to a path through a semantically organized discrete hierarchy. At inference time, we populate the index and use it to identify and retrieve clusters of sentences containing popular opinions from input reviews.
  arXiv  Detail & Related papers  (2024-03-01T10:38:07Z)
• Exploiting Contextual Target Attributes for Target Sentiment Classification [53.30511968323911]
  Existing PTLM-based models for TSC can be categorized into two groups: 1) fine-tuning-based models that adopt PTLM as the context encoder; 2) prompting-based models that transfer the classification task to the text/word generation task. We present a new perspective of leveraging PTLM for TSC: simultaneously leveraging the merits of both language modeling and explicit target-context interactions via contextual target attributes.
  arXiv  Detail & Related papers  (2023-12-21T11:45:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.