keyplayer: An R Package for Locating Key Players in Social Networks

Abstract

Interest in social network analysis has exploded in the past few years, partly thanks to the advancements in statistical methods and computing for network analysis. A wide range of the methods for network analysis is already covered by existent R packages. However, no comprehensive packages are available to calculate group centrality scores and to identify key players (i.e., those players who constitute the most central group) in a network. These functionalities are important because, for example, many social and health interventions rely on key players to facilitate the intervention. Identifying key players is challenging because players who are individually the most central are not necessarily the most central as a group due to redundancy in their connections. In this paper we develop methods and tools for computing group centrality scores and for identifying key players in social networks. We illustrate the methods using both simulated and empirical examples. The package keyplayer providing the presented methods is available from Comprehensive R Archive Network (CRAN).

Application of network analysis to investigate sex differences in interactive systems of eating‐disorder psychopathology

“…Key players analysis (Borgatti, ) was used to identify differences in fragmentation between the two networks. The R package keyplayeR (An & Liu, ) analyzes weighted networks to identify a set of “key players” that leads to maximal fracturing of the network when removed. Fragmentation of the network upon removal of the key players has been quantified as fragmentation values.…”

Single‐node vs. multi‐node centrality in landscape graph analysis: key habitat patches and their protection for 20 bird species in NE Spain

“…The KP method identifies the most central set of nodes in a network according to eight different centrality metrics (An & Liu ). We focus on two of these metrics, which correspond to finding the optimal set of nodes for two distinct purposes:…”

“…It focuses only on reaching all parts of the network, whether or not they are close to large patches. fragmentation centrality (KP F ): disrupts the connectivity of the network by removing key nodes. Here, the aim is to identify the set of n nodes which, if removed, would maximally lengthen the distances (here decrease p ij *) among the remaining nodes, resulting in maximal fragmentation (Borgatti ; An & Liu ), in order to protect these patches first. The KP F set, like dPC, is determined through removal experiments.…”

“…). The KeyPlayer (KP) algorithm (Borgatti ; Benedek, Jordán & Báldi ; An & Liu ) aims to overcome the problem of exhaustive search by means of a heuristic search method, which increases processing efficiency in multi‐node analysis of larger networks. Several centrality metrics may be used for multi‐node analysis with KP (An & Liu ).…”

“…In this study, we use and compare network analytical techniques and centrality‐related metrics evaluating single or multiple nodes in networks. In particular, we set priorities using single‐node rankings based on the connector fraction of PC (Saura & Rubio ) and on multi‐node selection using two centrality metrics currently implemented in the KP algorithm (Borgatti ; An & Liu ). To evaluate these approaches in real‐world conditions, we (i) analyse landscape connectivity for 20 bird species of different conservation status in Catalonia, Spain; (ii) evaluate the overlap between the Natura 2000 network of protected areas and the habitat of the species; (iii) identify the critical habitat patches for connectivity for each species using PC and KP; (iv) assess the coverage of critical patches from single‐ and multi‐node approaches by the Natura 2000 network and finally and (v) provide a multi‐species and multi‐approach solution to landscape management.…”