User Review Writing via Interview with Dialogue Systems

TL;DR

This paper introduces a dialogue system-based approach using GPT-4 to assist users in creating detailed reviews efficiently, showing improved helpfulness and reduced editing needs compared to traditional methods.

Contribution

The study presents a novel application of dialogue systems for automated review generation, validated through experiments demonstrating enhanced review helpfulness and user satisfaction.

Findings

Participants rated their interactions positively.

Generated reviews required less editing for satisfaction.

System reviews were more helpful than human-written ones.

Abstract

User reviews on e-commerce and review sites are crucial for making purchase decisions, although creating detailed reviews is time-consuming and labor-intensive. In this study, we propose a novel use of dialogue systems to facilitate user review creation by generating reviews from information gathered during interview dialogues with users. To validate our approach, we implemented our system using GPT-4 and conducted comparative experiments from the perspectives of system users and review readers. The results indicate that participants who used our system rated their interactions positively. Additionally, reviews generated by our system required less editing to achieve user satisfaction compared to those by the baseline. We also evaluated the reviews from the reader' perspective and found that our system-generated reviews are more helpful than those written by humans. Despite challenges with the fluency of the generated reviews, our method offers a promising new approach to review writing.