Method for linking accounts in OSNs (On-line Social Networks)

Abstract

The invention discloses a method for linking accounts in a plurality of OSNs (On-line Social Networks) on the basis of node similarity. The friend relationship is extracted from OSN website accounts for linking the plurality of accounts, belonging to one real user, in different OSN platforms. The method comprises five parts: a data preprocessing part performs preprocessing on an account node relationship diagram of the OSNs; a node sequence extraction part obtains an account node sequence set through random walk; an account vector representation part generates a vector model of each account through a word to vector tool word2vec; a linear conversion matrix calculation part obtains a linear conversion matrix W from one OSN to another OSN by a gradient descent method; a linking account obtaining part maps the account in one OSN to a coordinate space of another OSN; and through similarity measure and threshold value screening, the linking accounts or a candidate set corresponding to all of the accounts are obtained. Errors of the account linking result caused by unreal feature information of the accounts are avoided, so that the account linking robustness is improved.

Description

technical field [0001] The invention belongs to the technical field of network information, and more specifically relates to a method for associating accounts in an online social network. Background technique [0002] Account association is the main technical method used to mine all possible account information of a user in various online social networks. It can be used to track malicious users who commit cybercrime to prevent the spread of malicious events, deeply mine account information to optimize recommendation methods, and detect After the account information is stolen, a danger warning will be issued to protect the account security of other websites. [0003] The features extracted by traditional account association methods include the personal information of the account itself such as gender, age, and geographic location, as well as user behavior rules such as text writing style, search term usage habits, and mouse dwell time. However, due to personal privacy, perso...

AI Technical Summary

Problems solved by technology

Although the traditional account association method completes the task of account association, the traditional account association method requires a lot of data input information, and it is difficult to avoid the deviation of the association result caused by false account information, so the robustness of the account association is not high.

Images