Probabilistic graphical models in modern social network analysis

Alireza Farasat, Alexander Nikolaev, Sargur N. Srihari, Rachael Hageman Blair
2015 Social Network Analysis and Mining  
2 Alireza Farasat et al. Abstract The advent and availability of technology has brought us closer than ever through social networks. Consequently, there is a growing emphasis on mining social networks to extract information for knowledge and discovery. However, methods for Social Network Analysis (SNA) have not kept pace with the data explosion. In this review, we describe directed and undirected Probabilistic Graphical Models (PGMs), and describe recent applications to social networks. Modern
more » ... NA is flooded with challenges that arise from the inherent size, scope, and heterogeneity of both the data and underlying population. As a flexible modeling paradigm, PGMs can be adapted to address some SNA challenges. Such challenges are common themes in Big Data applications, but must be carefully considered for reliable inference and modeling. For this reason, we begin with a thorough description of data collection and sampling methods, which are often necessary in social networks, and underlie any downstream modeling efforts. PGMs in SNA have been used to tackle current and relevant challenges, including the estimation and quantification of importance, propagation of influence, trust (and distrust), link and profile prediction, privacy protection, and news spread through micro-blogging. We highlight these applications, and others, to showcase the flexibility and predictive capabilities of PGMs in SNA. Finally, we conclude with a discussion of challenges and opportunities for PGMs in social networks.
doi:10.1007/s13278-015-0289-6 fatcat:ovrlvvfgonhttl65aqt7p3ckqq