End-to-End Aspect-Guided Review Summarization at Scale

2025-09-30

AI Summary

E-commerce review summarization suffers from insufficient interpretability and practical utility. Method: This paper proposes a guided summarization framework integrating Aspect-Based Sentiment Analysis (ABSA) with Large Language Models (LLMs). It first extracts high-frequency aspect–sentiment pairs and samples representative reviews to construct structured prompts, enabling LLMs to generate faithful, concise, and attributable summaries. Second, it introduces a lightweight real-time inference architecture for scalable online deployment. Contributions/Results: (1) The first large-scale public review dataset for home-eCommerce—comprising 11.8 million anonymized reviews across 92,000 products; (2) Significant improvements in user click-through rate and satisfaction, validated via rigorous A/B testing; (3) An open-source, reproducible ABSA+LLM collaborative summarization paradigm that jointly ensures accuracy, interpretability, and engineering scalability.

Technology Category

• Natural Language Processing: Summarization
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

We present a scalable large language model (LLM)-based system that combines aspect-based sentiment analysis (ABSA) with guided summarization to generate concise and interpretable product review summaries for the Wayfair platform. Our approach first extracts and consolidates aspect-sentiment pairs from individual reviews, selects the most frequent aspects for each product, and samples representative reviews accordingly. These are used to construct structured prompts that guide the LLM to produce summaries grounded in actual customer feedback. We demonstrate the real-world effectiveness of our system through a large-scale online A/B test. Furthermore, we describe our real-time deployment strategy and release a dataset of 11.8 million anonymized customer reviews covering 92,000 products, including extracted aspects and generated summaries, to support future research in aspect-guided review summarization.

Problem

• Generating concise product review summaries using aspect-guided approach
• Combining aspect-based sentiment analysis with large language models
• Scaling review summarization for e-commerce platforms with customer feedback

Innovation

• LLM-based system combining ABSA with guided summarization
• Extracts aspect-sentiment pairs and selects frequent aspects
• Uses structured prompts to generate customer-grounded summaries