End-to-End Aspect-Guided Review Summarization at Scale
This work addresses the need for automated review summarization for e-commerce platforms like Wayfair, though it is incremental as it builds on existing ABSA and LLM techniques.
The authors tackled the problem of generating concise and interpretable product review summaries by developing a scalable LLM-based system that combines aspect-based sentiment analysis with guided summarization, demonstrating real-world effectiveness through a large-scale online A/B test and releasing a dataset of 11.8 million reviews.
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.