User Review Writing via Interview with Dialogue Systems

2026-03-07

SIGDIAL Conferences

AI Summary

This work proposes an interview-style interactive approach based on a dialogue system to alleviate the time and effort required for users to write product reviews, thereby enhancing both the efficiency and quality of user-generated content on e-commerce platforms. For the first time in review generation, the method incorporates a dialogue-guided mechanism: the system engages users in multi-turn interactions to elicit key information and employs a GPT-4-powered generation module to automatically produce high-quality reviews. Experimental results demonstrate that this approach significantly reduces user authoring burden, yielding reviews that require fewer post-generation edits and are rated by readers as more helpful than those written entirely by humans, thus validating its effectiveness in improving both the efficiency and practical utility of review generation.

Technology Category

• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Interaction Techniques and Devices

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

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 readers’ 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.

Problem

• user review writing
• dialogue systems
• review generation
• e-commerce reviews
• human-AI interaction

Innovation

• dialogue systems
• review generation
• interview-based interaction
• GPT-4
• user-generated content