Improving amazon-like review systems by considering the credibility and time-decay of public reviews

Bo Chun Wang, Wen Yuan Zhu, Ling Jyh Chen

Research output: Contribution to journalReview article

2 Citations (Scopus)

Abstract

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 downloaded 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 review 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. Moreover, 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.

Original languageEnglish
Pages (from-to)463-472
Number of pages10
JournalInformatica (Ljubljana)
Volume35
Issue number4
Publication statusPublished - 2011

Keywords

  • Credibility
  • E-commerce
  • Review systems
  • Time-decay

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Computer Science Applications
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Improving amazon-like review systems by considering the credibility and time-decay of public reviews'. Together they form a unique fingerprint.

Cite this