A Multilevel Approach for Building Location-Based Social Network by using Stay Points

Diego Minatel, Vinícius Ferreira, Alneu de Andrade Lopes

Abstract: The main challenge of building Location-Based Social Network (LBSN) using stay points is the definition of local-vertices. Stay points are extracted from a GPS log and indicate that a user has remained in that place for a significant time. Usually, clustering techniques are employed to transform stay points into local-vertices. LBSNs built using stay points are richer in information since GPS logs have more user mobility information. It is usual building LBSN by using stay points, but there is room to discuss the approaches for construction of these networks. This article addresses this gap and presents a novel approach that uses the coarsening stage of a multilevel optimization scheme to build LBSNs by using stay points. The experimental evaluation carried out indicates that our approach has advantages when compared to usual clustering methods to representing real-world features.