E-commerce Query-based Generation based on User Review

TL;DR

This paper introduces a novel seq2seq model that automatically generates product-specific answers based on user reviews, improving e-commerce Q&A systems by summarizing relevant reviews conditioned on user questions and sentiment.

Contribution

The study presents a new attention-based seq2seq model with an auxiliary rating classifier for improved review-based answer generation in e-commerce.

Findings

Model outperforms previous approaches in accuracy.

Incorporating rating information enhances answer relevance.

Pre-trained classifier accelerates training convergence.

Abstract

With the increasing number of merchandise on e-commerce platforms, users tend to refer to reviews of other shoppers to decide which product they should buy. However, with so many reviews of a product, users often have to spend lots of time browsing through reviews talking about product attributes they do not care about. We want to establish a system that can automatically summarize and answer user's product specific questions. In this study, we propose a novel seq2seq based text generation model to generate answers to user's question based on reviews posted by previous users. Given a user question and/or target sentiment polarity, we extract aspects of interest and generate an answer that summarizes previous relevant user reviews. Specifically, our model performs attention between input reviews and target aspects during encoding and is conditioned on both review rating and input context during decoding. We also incorporate a pre-trained auxiliary rating classifier to improve model performance and accelerate convergence during training. Experiments using real-world e-commerce dataset show that our model achieves improvement in performance compared to previously introduced models.