Title
Detecting Internet Hidden Paid Posters Based on Group and Individual Characteristics.
Abstract
Online social networks are popular communication tools for billions of users. Unfortunately, they are also effective tools for hidden paid posters (or Internet water army in some literatures) to propagate spam or mendacious messages. Paid posters are typically organized in groups to post with specific purposes and have flooded the communities of microblogging websites. Typical traditional methods only utilize individual characteristics in detecting them. In this paper, we study the group characteristics of paid posters and find that group characteristics are also very important in detecting them comparing to individual characteristics. We construct a classifier based on both the individual and group characteristics to detect paid posters. Extensive experiments show that our method is better than existing methods.
Year
Venue
Field
2015
WISE
World Wide Web,Social network,Social media,Computer science,Microblogging,Classifier (linguistics),The Internet
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
14
4
Name
Order
Citations
PageRank
Xiang Wang103.04
Bin Zhou261.08
yan34911.67
Shasha Li453.52