Abstract | ||
---|---|---|
Social media have become popular communication platforms in recent years. A huge number of users disseminate and share information on these websites. Due to their popularity, social media have attracted numerous malicious users (spammers) to send spams, spread malware and phish scams. It is highly desirable to automatically distinguish legitimate users from spammers. Existing approaches mainly use behavior, content, or profile information as features to characterize the social spammers. However, to avoid being caught by the websites, the spammers pretend to post normal messages sometimes and change their behaviors continuously. This makes the behavior and content based approaches less effective. In this paper, we propose a novel method to detect social spammers via structural properties. Specifically, we adopt 12 types of topological features in users' ego network, including average degree, density, modularity, rich club connectivity, centrality, average shortest path, and cluster coefficient, to learn the classification model for spammer detection. Experimental results on a real world microblog data set demonstrate that the proposed method is very effective. It reaches an accuracy of 82.14% with only structural features. Furthermore, its performance can be significantly improved to 94.00% when combined with other features. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-981-10-2993-6_21 | Communications in Computer and Information Science |
Keywords | DocType | Volume |
Spammer detection,Structural properties,Ego network | Conference | 669 |
ISSN | Citations | PageRank |
1865-0929 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Baochao Zhang | 1 | 0 | 0.68 |
Tieyun Qian | 2 | 177 | 28.81 |
Yiqi Chen | 3 | 0 | 0.34 |
Zhenni You | 4 | 2 | 2.05 |