MOSAIC: Modular Opinion Summarization using Aspect Identification and Clustering

TL;DR

MOSAIC is a modular opinion summarization framework that improves interpretability, aspect coverage, and faithfulness in review summarization, validated through online and offline experiments, and supported by a new dataset.

Contribution

We introduce MOSAIC, a scalable, modular approach for opinion summarization that emphasizes interpretability, aspect coverage, and robustness, including a novel opinion clustering component and a new dataset.

Findings

MOSAIC outperforms baselines in aspect coverage and faithfulness.

Opinion clustering significantly improves summarization quality.

Surfacing intermediate outputs enhances customer experience.

Abstract

Reviews are central to how travelers evaluate products on online marketplaces, yet existing summarization research often emphasizes end-to-end quality while overlooking benchmark reliability and the practical utility of granular insights. To address this, we propose MOSAIC, a scalable, modular framework designed for industrial deployment that decomposes summarization into interpretable components, including theme discovery, structured opinion extraction, and grounded summary generation. We validate the practical impact of our approach through online A/B tests on live product pages, showing that surfacing intermediate outputs improves customer experience and delivers measurable value even prior to full summarization deployment. We further conduct extensive offline experiments to demonstrate that MOSAIC achieves superior aspect coverage and faithfulness compared to strong baselines for summarization. Crucially, we introduce opinion clustering as a system-level component and show that it significantly enhances faithfulness, particularly under the noisy and redundant conditions typical of user reviews. Finally, we identify reliability limitations in the standard SPACE dataset and release a new open-source tour experience dataset (TRECS) to enable more robust evaluation.