Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

5-2016

Abstract

Summarizing patterns of connections or social tiesin a social network, in terms of attributes information on nodesand edges, holds a key to the understanding of how the actorsinteract and form relationships. We formalize this problem asmining top-k group relationships (GRs), which captures strongsocial ties between groups of actors. While existing works focuson patterns that follow from the well known homophily principle,we are interested in social ties that do not follow from homophily,thus, provide new insights. Finding top-k GRs faces new challenges:it requires a novel ranking metric because traditionalmetrics favor patterns that are expected from the homophilyprinciple; it requires an innovative search strategy since there isno obvious anti-monotonicity for such GRs; it requires a noveldata structure to avoid data explosion caused by multidimensionalnodes and edges and many-to-many relationships in a socialnetwork. We address these issues through presenting an efficientalgorithm, GRMiner, for mining top-k GRs and we evaluate itseffectiveness and efficiency using real data.

Discipline

Databases and Information Systems

Publication

IEEE 32nd International Conference on Data Engineering (ICDE) 2016: May 16-20, 2016, Helsinki, Finland: Proceedings

Identifier

10.1109/ICDE.2016.7498259

Publisher

IEEE

City or Country

Piscataway, NJ

Additional URL

https://doi.org/10.1109/ICDE.2016.7498259

Download

Share

COinS