Meta-path-based link prediction method for aligned heterogeneous social networks

Abstract

The invention discloses a meta-path-based link prediction method for aligned heterogeneous social networks, mainly solves the problem of link prediction (mainly including friend relationship prediction and position prediction) in the aligned heterogeneous social networks, and relates to related technologies of the aligned heterogeneous social networks, feature selection, link prediction and the like. The method mainly comprises six steps of (a) modeling the aligned heterogeneous social networks; (b) automatically extracting a meta-path; (c) defining a meta-path-based eigenvalue calculation method; (d) dividing data sets according to timestamps; (e) proposing a two-stage gradual forward greedy feature selection algorithm for performing feature selection; and (f) training a decision tree classifier based on a feature selection result to perform the link prediction. Based on the method, the aligned heterogeneous social networks consisting of Foursquare and Twitter are subjected to the link prediction; and the method has practical application values for entity recommendation, accurate marketing, criminal gang discovery and the like in the social networks.

Description

technical field [0001] The present invention is a meta-path-based link prediction method in a heterogeneous social network, which utilizes related technologies such as feature selection and link prediction, and relates to the field of social computing, especially link prediction. Background technique [0002] At first the relevant concepts involved in the present invention are defined: [0003] Heterogeneous social network: Given a social network N=(V,E), where V=V user ∪V non-user Represents a set of nodes, including a set of users V user and non-user node set V non-user , E=E user，user ∪E user，non-user ∪E non-user，non-user} is the set of edges between user nodes, between users and non-user nodes, and between non-user nodes, then N is called a heterogeneous social network; [0004] Anchor link: Given two heterogeneous social networks N i , N j and two accounts with which is with The set of user nodes belonging to two different heterogeneous social networks ...

AI Technical Summary

Problems solved by technology

[0014] In view of the fact that there are few related studies on link prediction in aligned heterogeneous social networks, and the existing research considers few factors, traditional link prediction methods such as collaborative filtering and matrix decomposition are difficult to solve the problem of data sparsity. Link prediction, feature selection and other related technologies, the present invention proposes a meta-path-based link prediction method in aligned heterogeneous social networks, which mainly solves the problem of user recommendation and location recommendation in aligned heterogeneous social networks

Images