Decomposed Opinion Summarization with Verified Aspect-Aware Modules

TL;DR

This paper introduces a modular, aspect-aware opinion summarization method that enhances explainability and grounding, outperforming baselines across diverse domains through improved summaries and intermediate outputs.

Contribution

A novel domain-agnostic modular framework for opinion summarization that explicitly incorporates review aspects for better transparency and interpretability.

Findings

Generated more grounded summaries than baseline models.

Produced more informative intermediate outputs.

Supported human review summarization with intermediate reasoning results.

Abstract

Opinion summarization plays a key role in deriving meaningful insights from large-scale online reviews. To make the process more explainable and grounded, we propose a domain-agnostic modular approach guided by review aspects (e.g., cleanliness for hotel reviews) which separates the tasks of aspect identification, opinion consolidation, and meta-review synthesis to enable greater transparency and ease of inspection. We conduct extensive experiments across datasets representing scientific research, business, and product domains. Results show that our approach generates more grounded summaries compared to strong baseline models, as verified through automated and human evaluations. Additionally, our modular approach, which incorporates reasoning based on review aspects, produces more informative intermediate outputs than other knowledge-agnostic decomposition approaches. Lastly, we provide empirical results to show that these intermediate outputs can support humans in summarizing opinions from large volumes of reviews.