MOSAIC: Modular Opinion Summarization using Aspect Identification and Clustering
This addresses the need for more interpretable and deployable summarization tools in online marketplaces, though it is incremental in its modular approach.
The paper tackled the problem of generating reliable and practical opinion summaries from reviews by proposing MOSAIC, a modular framework that improves aspect coverage and faithfulness, with online A/B tests showing measurable value in customer experience.
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.