@inproceedings{boytsov-etal-2025-end,
title = "End-to-End Aspect-Guided Review Summarization at Scale",
author = "Boytsov, Ilya and
DeGenova, Vinny and
Balyasin, Mikhail and
Walt, Joseph and
Eusden, Caitlin and
Rochat, Marie-Claire and
Pierson, Margaret",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.31/",
pages = "463--471",
ISBN = "979-8-89176-333-3",
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. 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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boytsov-etal-2025-end">
<titleInfo>
<title>End-to-End Aspect-Guided Review Summarization at Scale</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ilya</namePart>
<namePart type="family">Boytsov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinny</namePart>
<namePart type="family">DeGenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Balyasin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Walt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caitlin</namePart>
<namePart type="family">Eusden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Claire</namePart>
<namePart type="family">Rochat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margaret</namePart>
<namePart type="family">Pierson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou (China)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-333-3</identifier>
</relatedItem>
<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. 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.</abstract>
<identifier type="citekey">boytsov-etal-2025-end</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.31/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>463</start>
<end>471</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T End-to-End Aspect-Guided Review Summarization at Scale
%A Boytsov, Ilya
%A DeGenova, Vinny
%A Balyasin, Mikhail
%A Walt, Joseph
%A Eusden, Caitlin
%A Rochat, Marie-Claire
%A Pierson, Margaret
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F boytsov-etal-2025-end
%X 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. 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.
%U https://aclanthology.org/2025.emnlp-industry.31/
%P 463-471
Markdown (Informal)
[End-to-End Aspect-Guided Review Summarization at Scale](https://aclanthology.org/2025.emnlp-industry.31/) (Boytsov et al., EMNLP 2025)
ACL
- Ilya Boytsov, Vinny DeGenova, Mikhail Balyasin, Joseph Walt, Caitlin Eusden, Marie-Claire Rochat, and Margaret Pierson. 2025. End-to-End Aspect-Guided Review Summarization at Scale. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 463–471, Suzhou (China). Association for Computational Linguistics.