Combining contextual, temporal and topological information for unsupervised link prediction in social networks

Abstract Understanding and characterizing the processes driving social interactions is one of the fundamental problems in social network analysis. In this context, link prediction aims to foretell whether two not linked nodes in a network will connect in the near future. Several studies proposed to solve link prediction compute compatibility degrees as link weights between connected nodes and, based on a weighted graph, apply weighted similarity functions to non-connected nodes in order to identify potential new links. The weighting criteria used by those studies were based exclusively on information about the existing topology (network structure). Nevertheless, such approach leads to poor incorporation of other aspects of the social networks, such as context (node and link attributes), and temporal information (chronological interaction data). Hence, in this paper, we propose three weighting criteria that combine contextual, temporal and topological information in order to improve results in link prediction. We evaluated the proposed weighting criteria with two popular weighted similarity functions (Adamic-Adar and Common Neighbors) in ten networks frequently used in experiments with link prediction. Results with the proposed criteria were statistically better than the ones obtained from the weighting criterion that is exclusively based on topological information.

[1]  Linyuan Lu,et al.  Link Prediction in Complex Networks: A Survey , 2010, ArXiv.

[2]  M. Jackson,et al.  An Economic Model of Friendship: Homophily, Minorities and Segregation , 2007 .

[3]  Alexander J. Smola,et al.  Like like alike: joint friendship and interest propagation in social networks , 2011, WWW.

[4]  Jennifer Neville,et al.  Modeling relationship strength in online social networks , 2010, WWW '10.

[5]  Christopher M. Danforth,et al.  An evolutionary algorithm approach to link prediction in dynamic social networks , 2013, J. Comput. Sci..

[6]  Rossano Schifanella,et al.  Friendship prediction and homophily in social media , 2012, TWEB.

[7]  Mark S. Granovetter.  The Strength of Weak Ties , 1973, American Journal of Sociology.

[8]  Mohammad Al Hasan,et al.  Link prediction using supervised learning , 2006 .

[9]  Tao Zhou,et al.  Link prediction in weighted networks: The role of weak ties , 2010 .

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

[11]  Maria Cláudia Reis Cavalcanti,et al.  Automatic feature selection for supervised learning in link prediction applications: a comparative study , 2017, Knowledge and Information Systems.

[12]  Tamara G. Kolda,et al.  Temporal Link Prediction Using Matrix and Tensor Factorizations , 2010, TKDD.

[13]  Shyhtsun Felix Wu,et al.  Analysis of user keyword similarity in online social networks , 2011, Social Network Analysis and Mining.

[14]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[15]  Ryutaro Ichise,et al.  Time Score: A New Feature for Link Prediction in Social Networks , 2012, IEICE Trans. Inf. Syst..

[16]  Olivia R. Liu Sheng,et al.  A Survey of Link Recommendation for Social Networks , 2015, ACM Trans. Manag. Inf. Syst..

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

[18]  Dongfeng Yuan,et al.  Deep Learning Based Link Prediction with Social Pattern and External Attribute Knowledge in Bibliographic Networks , 2016, 2016 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData).

[19]  Cecilia Mascolo,et al.  Temporal distance metrics for social network analysis , 2009, WOSN '09.

[20]  Fernando Berzal Galiano,et al.  A Survey of Link Prediction in Complex Networks , 2016, ACM Comput. Surv..

[21]  Ricardo Choren,et al.  Using a Time based Relationship Weighting Criterion to Improve Link Prediction in Social Networks , 2017, ICEIS.

[22]  Srikanta J. Bedathur,et al.  Towards time-aware link prediction in evolving social networks , 2009, SNA-KDD '09.

[23]  Aram Galstyan,et al.  Scalable Temporal Latent Space Inference for Link Prediction in Dynamic Social Networks (Extended Abstract) , 2017, 2017 IEEE 33rd International Conference on Data Engineering (ICDE).

[24]  Peng Wang,et al.  Link prediction in social networks: the state-of-the-art , 2014, Science China Information Sciences.

[25]  Jie Tang,et al.  Link Prediction of Social Networks Based on Weighted Proximity Measures , 2007, IEEE/WIC/ACM International Conference on Web Intelligence (WI'07).

[26]  Matthew Rowe,et al.  Who Will Follow Whom? Exploiting Semantics for Link Prediction in Attention-Information Networks , 2012, SEMWEB.

[27]  Cecilia Mascolo,et al.  Exploiting place features in link prediction on location-based social networks , 2011, KDD.

[28]  Alneu de Andrade Lopes,et al.  A naïve Bayes model based on overlapping groups for link prediction in online social networks , 2015, SAC.

[29]  Mohammad Al Hasan,et al.  A Survey of Link Prediction in Social Networks , 2011, Social Network Data Analytics.

[30]  Ricardo B. C. Prudêncio,et al.  Proximity measures for link prediction based on temporal events , 2013, Expert Syst. Appl..

[31]  Rong Zeng,et al.  Link prediction based on dynamic weighted social attribute network , 2016, 2016 International Conference on Machine Learning and Cybernetics (ICMLC).