Structural analysis in multi-relational social networks

• Main Authors: DAI, Bing Tian, CHUA, Freddy Chong Tat, LIM, Ee-peng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2012
• Subjects: Databases and Information Systems; Social Media
• Online Access: https://ink.library.smu.edu.sg/sis_research/3718; https://ink.library.smu.edu.sg/context/sis_research/article/4720/viewcontent/1978161197282539.pdf
• Institution: Singapore Management University

Modern social networks often consist of multiple relationsamong individuals. Understanding the structureof such multi-relational network is essential. In sociology,one way of structural analysis is to identify differentpositions and roles using blockmodels. In thispaper, we generalize stochastic blockmodels to GeneralizedStochastic Blockmodels (GSBM) for performing positionaland role analysis on multi-relational networks.Our GSBM generalizes many different kinds of MultivariateProbability Distribution Function (MVPDF) tomodel different kinds of multi-relational networks. Inparticular, we propose to use multivariate Poisson distributionfor multi-relational social networks. Our experimentsshow that GSBM is able to identify the structuresfor both synthetic and real world network data.These structures can further be used for predicting relationshipsbetween individuals.