Collective Hyping Detection System for Identifying Online Spam Activities

Publication Type:
Journal Article
Citation:
IEEE Intelligent Systems, 2017
Issue Date:
2017-06-14
Full metadata record
Files in This Item:
Filename Description Size
x5zhang.final.Intelligent-Systems.pdfAccepted Manuscript1.35 MB
Adobe PDF
IEEE Online reviews are extensively utilized by potential buyers to make business decisions. Unfortunately, fraudsters offer to write spam reviews for product promotion or competitor defamation, which drives online business holders to adopt this type of vicious strategy to increase their profits. These fake reviews always mislead users who shop online. Though existing anti-spam strategies have been proved to be effective in detecting traditional spam activities, evolving spam schemes can successfully cheat conventional testing by buying the comments of a massive number of random but genuine users which are sold by specific web markets, i.e., User Cloud. A more crucial problem is that such spam activities turn into a kind of 'advertising campaign' among business owners as they need to maintain their rank in the top few positions. In this paper, we propose a new Collaborative Marketing Hyping Detection solution, which aims to identify spam comments generated by the Spam Reviewer Cloud and to detect products which adopt an evolving spam strategy for promotion. Our experiments validate the existence of the Collaborative Marketing Hyping activities on a real-life e-commercial platform and also demonstrate that our model can effectively and accurately identify these advanced spam activities.
Please use this identifier to cite or link to this item: