文章基本信息

标题：Improving Amazon-like Review Systems by Considering the Credibility and Time-Decay of Public Reviews
本地全文：下载
作者：B.-C. Wang ; W.-Y. Zhu ; L.-J. Chen 等
期刊名称：Informatica
印刷版ISSN：1514-8327
电子版ISSN：1854-3871
出版年度：2011
卷号：35
期号：4
出版社：The Slovene Society Informatika, Ljubljana
摘要：In this study, we investigate the review system of Amazon.com, which is regarded as one of the most successful e-commerce websites in the world. We believe that the review results provided by Amazon’s review system may not be representative of the advertised products because the system does not consider two essential factors, namely the credibility and the time-decay of public reviews. Using a dataset down- loaded from Amazon.com, we demonstrate that although the credibility and time-decay issues are very common, they are not handled well by current public review systems. To address the situation, we propose a Review-credibility and Time-decay Based Ranking (RTBR) approach, which improves the Amazon re- view system by exploiting the credibility and time-decay of reviews posted by the public. We evaluate the proposed scheme against the current Amazon scheme. The results demonstrate that the RTBR scheme is superior to the Amazon scheme because it is more credible and it provides timely review results. More- over, the scheme is simple and applicable to other Amazon-like review systems in which the reviews are time-stamped and can be evaluated by other users.
关键词：review systems; credibility; time-decay; e-commerce