Are the most popular users always trustworthy? The case of Yelp
作者：
Highlights：
• Empirical proof that the most popular users do not always provide trustworthy ratings.
• The highest trustworthiness percentage of these users is at 83.4% without outliers filtering.
• With outliers filtering, this trustworthiness percentage is reduced to 78.5%.
• Proof that users should not rely solely on popular users’ ratings when determining trustworthiness.
摘要
•Empirical proof that the most popular users do not always provide trustworthy ratings.•The highest trustworthiness percentage of these users is at 83.4% without outliers filtering.•With outliers filtering, this trustworthiness percentage is reduced to 78.5%.•Proof that users should not rely solely on popular users’ ratings when determining trustworthiness.
论文关键词：Electronic commerce,Ratings,Reputation system,Trust,Trust circle,Data mining,Machine learning,Clustering,Yelp
论文评审过程：Received 17 February 2016, Revised 31 August 2016, Accepted 13 September 2016, Available online 15 September 2016, Version of Record 20 September 2016.
论文官网地址：https://doi.org/10.1016/j.elerap.2016.09.005
