Efficiently Promoting Product Online Outcome: An Iterative Rating Attack Utilizing Product and Market Property (Jun-2017)
The aim of the project is e-commerce and social media, online rating systems that let users post ratings/reviews of products. In case product rating/reviews malicious vendors to mislead to in set the fake rating and reviews. Our aim is to identify the unfair rating and review that product.
In addition, a variety of advanced defenses are proposed to statistically analyze products’ rating distributions, to evaluate raters’ feedback trust ,and to adopt temporal and user similarity information in unfair rating detection, where Qα (y|x) denotes the αth quantile of the distribution of the outcome variable y, and x denotes the vector of independent variables. Online user ratings thus play a significant role in making a product visible out of abundant product choices. CNETD clearly displays the average rating star and the total number of user ratings for each listed product and updates that information daily, ex: we collect weekly data of software downloads and online user ratings from CNETD over 26 weeks in four categories from August 2007 to February 2008. Those categories are, moblie, which are chosen to include both popular downloaded software programs as well as software programs with different application purposes., Specifically, we collect the number of weekly downloads (d i t ), the cumulative number of downloads, the average rating values (r¯ i t ), the rating volume, how long the software has been available on the market, and product rank by weekly downloads, in addition to various software characteristics. Moreover, prior studies in the same context have found that being selected by CNET editors sends a positive signal to online users, leading to greater downloads.