Link prediction based on dynamic weighted social attribute network

Social networks are highly dynamic objects; they grow and change quickly over time through the addition of new edges, signifying the appearance of new interactions in the underlying social structure. In present online social networks have become necessary communication tools in peoples' daily life. Links prediction of social network can not only recommend future friends to a user, but also can predict large scale social trends. In this paper, the link prediction problem is treated as a binary classification problem. We propose the method for constructing dynamic weighted social attribute network, and then extract different features from the weighted social attribute network, which are used to train a classifier for link prediction. Moreover, we discuss how to design the node weight and edge weight. The experiments show that when compared with the original social attribute network graph, the weighted social attribute network has better performance for link prediction, and the method for designing the weight of the node and edge weight of the social attribute network is feasible.

[1]  David Liben-Nowell,et al.  The link-prediction problem for social networks , 2007 .

[2]  Mohsen Jamali,et al.  Different Aspects of Social Network Analysis , 2006, 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings)(WI'06).

[3]  Nitesh V. Chawla,et al.  New perspectives and methods in link prediction , 2010, KDD.

[4]  Jiawei Han,et al.  A Unified Framework for Link Recommendation Using Random Walks , 2010, 2010 International Conference on Advances in Social Networks Analysis and Mining.

[5]  M. Newman.  Clustering and preferential attachment in growing networks. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[6]  M. Newman.  Analysis of weighted networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  Jure Leskovec,et al.  Supervised random walks: predicting and recommending links in social networks , 2010, WSDM '11.

[8]  Isaac Olusegun Osunmakinde,et al.  Temporality in Link Prediction: Understanding Social Complexity , 2009 .

[9]  Ling Huang,et al.  Joint Link Prediction and Attribute Inference Using a Social-Attribute Network , 2014, TIST.

[10]  M. Newman,et al.  Vertex similarity in networks. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[11]  Jianquan Liu,et al.  Link prediction: the power of maximal entropy random walk , 2011, CIKM '11.

[12]  Frank M. Shipman,et al.  Link prediction applied to an open large-scale online social network , 2010, HT '10.

[13]  Guojun Liu,et al.  Evolution of Social Networks: New Patterns and a New Generator , 2011, 2011 Ninth International Conference on Creating, Connecting and Collaborating through Computing.

[14]  Isaac Olusegun Osunmakinde,et al.  Temporality in link prediction , 2009 .