arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.07070cs.HCcs.AI
收藏

通过对话系统进行用户评论写作

User Review Writing via Interview with Dialogue Systems

The University of Electro-Communications(电通大学)

Yoshiki Tanaka, Michimasa Inaba

AI总结:

本文提出通过对话系统生成用户评论,实验表明该方法能提高评论生成效率并提升用户满意度。

摘要:

电子商务和评论网站上的用户评论对做出购买决策至关重要,尽管创建详细的评论是耗时且劳动密集的。在本研究中,我们提出了一种新颖的对话系统应用,通过与用户进行对话收集信息来促进用户评论的创建。为了验证我们的方法,我们使用GPT-4实现了我们的系统,并从系统用户和评论读者的角度进行了比较实验。结果表明,使用我们系统的参与者对互动评价持积极态度。此外,由我们的系统生成的评论比基线方法所需的编辑工作更少,以达到用户满意度。我们还从读者的角度评估了评论,并发现我们的系统生成的评论比人类撰写的评论更有帮助。尽管生成评论的流畅性存在挑战,我们的方法提供了一种有前途的评论写作新方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑