Title
A unified framework for detecting author spamicity by modeling review deviation.
Abstract
•Dealing with review spammer detection problem.•We propose an unified framework for detecting author spamicity.•A set of abnormity signals were proposed from deviation angle.•An aspect-based deviation was designed to model latent content deviation.•Experimental results suggest that our approach is appropriate for this task.
Year
DOI
Venue
2018
10.1016/j.eswa.2018.06.028
Expert Systems with Applications
Keywords
Field
DocType
Review spam,Spam detection techniques,Fake reviews,Bidirectional LSTM,Review deviation
Data mining,Ranking,Computer science,Outlier,Customer reviews,Spamming
Journal
Volume
ISSN
Citations 
112
0957-4174
2
PageRank 
References 
Authors
0.36
29
2
Name
Order
Citations
PageRank
Yuanchao Liu1369.89
Bo Pang25795451.00