PROJECT TITLE :

Structure Based User Identification across Social Networks - 2018

ABSTRACT:

Identification of anonymous identical users of cross-platforms refers to the recognition of the accounts belonging to the same individual among multiple Social Network (SN) platforms. Evidently, cross-platform exploration might help solve several issues in social computing, in each theory and apply. But, it's still an intractable drawback thanks to the fragmentation, inconsistency, and disruption of the accessible info among SNs. Different from the efforts implemented on user profiles and users' content, many studies have noticed the accessibility and reliability of network structure in most of the SNs for addressing this issue. Although substantial achievements are made, most of this network structure-based mostly solutions, requiring previous knowledge of some given identified users, are supervised or semi-supervised. It is laborious to label the previous knowledge manually in some eventualities where previous data is hard to obtain. Noticing that friend relationships are reliable and consistent in several SNs, we proposed an unsupervised theme, termed Friend Relationship-based User Identification algorithm while not Previous data (FRUI-P). The FRUI-P initial extracts the friend feature of each user in an SN into friend feature vector, and then calculates the similarities of all the candidate identical users between 2 SNs. Finally, a 1-to-one map scheme is developed to identify the users based mostly on the similarities. Moreover, FRUI-P is proved to be economical theoretically. Results of extensive experiments demonstrated that FRUI-P performs a lot of better than current state-of-art network structure-based mostly algorithm while not prior data. Because of its high precision, FRUI-P can additionally be utilised to get prior data for supervised and semi-supervised schemes. In applications, the unsupervised anonymous identical user identification method accommodates a lot of situations where the seed users are unobtainable.