Inferring Offline Hierarchical Ties From Online Social Networks

Social networks can represent many different types of relationships between actors, some explicit and some implicit. For example, email communications between users may be represented explicitly in a network, while managerial relationships may not. In this paper we focus on analyzing explicit interactions among actors in order to detect hierarchical social relationships that may be implicit. We start by employing three well-known ranking-based methods, PageRank, Degree Centrality, and Rooted-PageRank (RPR) to infer such implicit relationships from interactions between actors. Then we propose two novel approaches which take into account the time-dimension of interactions in the process of detecting hierarchical ties. We experiment on two datasets, the Enron email dataset to infer manager-subordinate relationships from email exchanges, and a scientific publication co-authorship dataset to detect PhD advisor-advisee relationships from paper co-authorships. Our experiments show that time-based methods perform considerably better than ranking-based methods. In the Enron dataset, they detect 48% of manager-subordinate ties versus 32% found by Rooted-PageRank. Similarly, in co-author dataset, they detect 62% of advisor-advisee ties compared to only 39% by Rooted-PageRank.