Authors:
Aleksei Romanov
;
Alexander Semenov
and
Jari Veijalainen
Affiliation:
University of Jyväskylä, Finland
Keyword(s):
Social Network Analysis, Anomaly Detection, Suspicious Behaviour, Graph Mining, Longitudinal Data.
Related
Ontology
Subjects/Areas/Topics:
Social Media Analytics
;
Society, e-Business and e-Government
;
Web Information Systems and Technologies
Abstract:
The goal of the current research is to detect fake identities among newly registered users of vk.com. Ego networks in vk.com for about 200.000 most recently registered profiles were gathered and analyzed longitudinally. The reason is that a certain percentage of new user accounts are faked, and the faked accounts and normal accounts have different behavioural patterns. Thus, the former can be detected already in a few first days. Social graph metrics were calculated and analysis was performed that allowed to reveal outlying suspicious profiles, some of which turned out to be legitimate celebrities, but some were fake profiles involved in social media marketing and other malicious activities, as participation in friend farms.