paper-with-me

홈 › Papers

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

2025-09-30 · Ilya Boytsov, Vinny DeGenova, Mikhail Balyasin, Joseph Walt, Caitlin Eusden, Marie-Claire Rochat, Margaret Pierson arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.26103

Code (0)

등록된 구현이 없습니다.

Tasks

Sentiment Analysis

Similar Papers 제목 키워드 기반

Aspect-Aware Decomposition for Opinion Summarization

2025-01-27 · Miao Li, Jey Han Lau, Eduard Hovy, Mirella Lapata

Opinion summarization plays a key role in deriving meaningful insights from large-scale online reviews. To make this process more explainable and grounded, we propose a modular approach guided by review aspects which sep…

Opinion Summarization

Unsupervised Aspect-Based Multi-Document Abstractive Summarization

2019-11-01 · WS 2019 11 · Maximin Coavoux, Hady Elsahar, Matthias Gall{\'e}

User-generated reviews of products or services provide valuable information to customers. However, it is often impossible to read each of the potentially thousands of reviews: it would therefore save valuable time to pro…

Abstractive Text SummarizationClusteringDocument SummarizationLanguage Modeling+3

Prompted Aspect Key Point Analysis for Quantitative Review Summarization

2024-07-19 · An Quang Tang, Xiuzhen Zhang, Minh Ngoc Dinh, Erik Cambria

Key Point Analysis (KPA) aims for quantitative summarization that provides key points (KPs) as succinct textual summaries and quantities measuring their prevalence. KPA studies for arguments and reviews have been reporte…

In-Context LearningSentiment Analysis

WikiAsp: A Dataset for Multi-domain Aspect-based Summarization

2020-11-16 · Hiroaki Hayashi, Prashant Budania, Peng Wang, Chris Ackerson 외

Aspect-based summarization is the task of generating focused summaries based on specific points of interest. Such summaries aid efficient analysis of text, such as quickly understanding reviews or opinions from different…

Articles

Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization

2023-03-21 · Ming Shen, Jie Ma, Shuai Wang, Yogarshi Vyas 외

Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews. However, generating aspect-specific and general summaries is challenging due to the lack of annotat…

Natural Language InferenceOpinion SummarizationUnsupervised Opinion Summarization