From Reviews to Actionable Insights: An LLM-Based Approach for Attribute and Feature Extraction
Khaled Boughanmi, Kamel Jedidi, Nour Jedidi
TL;DR
The paper introduces a systematic, LLM-based pipeline to extract perceptual attributes and actionable features from customer reviews, grounded in marketing theory and the means–end framework. It uses a three-step process: (1) exploratory generation of a concise attribute/feature dictionary, (2) confirmatory extraction of attribute/feature mentions and sentiments with context-aware prompting, and (3) derivation of actionable insights and dashboard visualizations. Validation against human coders shows high agreement and strong predictive validity for ratings, with GPT-4.1 mini, sentence-level prompts delivering the best reliability and interpretability at scale. Store- and feature-level analyses identify key drivers of satisfaction (notably staff professionalism and efficiency, beverage quality, and store environment) and quantify potential revenue gains from targeted improvements, enabling data-driven turnarounds across stores and domains.
Abstract
This research proposes a systematic, large language model (LLM) approach for extracting product and service attributes, features, and associated sentiments from customer reviews. Grounded in marketing theory, the framework distinguishes perceptual attributes from actionable features, producing interpretable and managerially actionable insights. We apply the methodology to 20,000 Yelp reviews of Starbucks stores and evaluate eight prompt variants on a random subset of reviews. Model performance is assessed through agreement with human annotations and predictive validity for customer ratings. Results show high consistency between LLMs and human coders and strong predictive validity, confirming the reliability of the approach. Human coders required a median of six minutes per review, whereas the LLM processed each in two seconds, delivering comparable insights at a scale unattainable through manual coding. Managerially, the analysis identifies attributes and features that most strongly influence customer satisfaction and their associated sentiments, enabling firms to pinpoint "joy points," address "pain points," and design targeted interventions. We demonstrate how structured review data can power an actionable marketing dashboard that tracks sentiment over time and across stores, benchmarks performance, and highlights high-leverage features for improvement. Simulations indicate that enhancing sentiment for key service features could yield 1-2% average revenue gains per store.