Abstract
In this paper we investigate on detecting opinion spammer groups through analyzing how users interact with each other. More specifically, our approaches are based on 1) discovering strong vs. weak implicit communities by mining user interaction patterns, and 2) revealing positive vs. negative communities through sentiment analysis on user interactions. Through extensive experiments over various datasets collected from Amazon, we found that the discovered strong, positive communities are significantly more likely to be opinion spammer groups than other communities. Interestingly, while our approach focused mainly on the characteristics of user interactions, it is comparable to the state of the art content-based classifier that mainly uses various content-based features extracted from user reviews. More importantly, we argue that our approach can be more robust than the latter in that if spammers superficially alter their review contents, our approach can still reliably identify them while the content-based approaches may fail.
| Original language | English |
|---|---|
| Pages (from-to) | 283-318 |
| Number of pages | 36 |
| Journal | Journal of Computer Security |
| Volume | 25 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 1 Jan 2017 |
Fingerprint
Keywords
- community discovery
- Opinion spammer groups
- sentiment analysis
ASJC Scopus subject areas
- Software
- Safety, Risk, Reliability and Quality
- Hardware and Architecture
- Computer Networks and Communications
Cite this
Detecting opinion spammer groups and spam targets through community discovery and sentiment analysis. / Choo, Euijin; Yu, Ting; Chi, Min.
In: Journal of Computer Security, Vol. 25, No. 3, 01.01.2017, p. 283-318.Research output: Contribution to journal › Review article
}
TY - JOUR
T1 - Detecting opinion spammer groups and spam targets through community discovery and sentiment analysis
AU - Choo, Euijin
AU - Yu, Ting
AU - Chi, Min
PY - 2017/1/1
Y1 - 2017/1/1
N2 - In this paper we investigate on detecting opinion spammer groups through analyzing how users interact with each other. More specifically, our approaches are based on 1) discovering strong vs. weak implicit communities by mining user interaction patterns, and 2) revealing positive vs. negative communities through sentiment analysis on user interactions. Through extensive experiments over various datasets collected from Amazon, we found that the discovered strong, positive communities are significantly more likely to be opinion spammer groups than other communities. Interestingly, while our approach focused mainly on the characteristics of user interactions, it is comparable to the state of the art content-based classifier that mainly uses various content-based features extracted from user reviews. More importantly, we argue that our approach can be more robust than the latter in that if spammers superficially alter their review contents, our approach can still reliably identify them while the content-based approaches may fail.
AB - In this paper we investigate on detecting opinion spammer groups through analyzing how users interact with each other. More specifically, our approaches are based on 1) discovering strong vs. weak implicit communities by mining user interaction patterns, and 2) revealing positive vs. negative communities through sentiment analysis on user interactions. Through extensive experiments over various datasets collected from Amazon, we found that the discovered strong, positive communities are significantly more likely to be opinion spammer groups than other communities. Interestingly, while our approach focused mainly on the characteristics of user interactions, it is comparable to the state of the art content-based classifier that mainly uses various content-based features extracted from user reviews. More importantly, we argue that our approach can be more robust than the latter in that if spammers superficially alter their review contents, our approach can still reliably identify them while the content-based approaches may fail.
KW - community discovery
KW - Opinion spammer groups
KW - sentiment analysis
UR - http://www.scopus.com/inward/record.url?scp=85020095578&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85020095578&partnerID=8YFLogxK
U2 - 10.3233/JCS-16941
DO - 10.3233/JCS-16941
M3 - Review article
VL - 25
SP - 283
EP - 318
JO - Journal of Computer Security
JF - Journal of Computer Security
SN - 0926-227X
IS - 3
ER -