PREFER: Personalized Review Summarization with Online Preference Learning

2026-05-07

AI Summary

Existing e-commerce review summarization systems produce static and generic summaries that fail to accommodate users’ personalized interests in product attributes or their dynamically evolving preferences. This work introduces online preference learning into personalized review summarization for the first time, proposing a framework that integrates online learning with personalized text generation. By continuously incorporating user feedback on generated summaries, the model updates latent preference representations in real time and dynamically refines subsequent outputs. Simulations on the Amazon Reviews'23 dataset demonstrate that the proposed approach significantly improves alignment between summaries and individual user interests while maintaining high-quality text generation.

Abstract

Product reviews significantly influence purchasing decisions on e-commerce platforms. However, the sheer volume of reviews can overwhelm users, obscuring the information most relevant to their specific needs. Current e-commerce summarization systems typically produce generic, static summaries that fail to account for the fact that (i) different users care about different product characteristics, and (ii) these preferences may evolve with interactions. To address the challenge of unknown latent preferences, we propose an online learning framework that generates personalized summaries for each user. Our system iteratively refines its understanding of user preferences by incorporating feedback directly from the generated summaries over time. We provide a case study using the Amazon Reviews'23 dataset, showing in controlled simulations that online preference learning improves alignment with target user interests while maintaining summary quality.

Problem

• personalized summarization
• user preferences
• online learning
• product reviews
• e-commerce

Innovation

• personalized summarization
• online preference learning
• user feedback
• review summarization
• adaptive personalization