Node and edge removal on complex networks in labor market research and their influence on centrality measures

Abstract

„This research examines the impact of node and edge removal strategies on centrality measures within complex networks. Investigating random, scale-free, and small-world networks, various removal approaches, including targeted and random removal, are evaluated. The study assesses their influence on centrality metrics such as degree, betweenness, closeness, and eigenvector centrality on random networks and networks from educational research describing longitudinal data in labor market-related topics in social networks. The findings contribute insights applicable across domains. In social network analysis, an understanding of key actors is beneficial for the development of targeted interventions or marketing strategies. Historical network analyses benefit from the discernment of pivotal nodes or connections, which elucidate information flow or influential figures across different periods. Such applications underscore the significance of the research in optimizing network performance in diverse contexts.“ (authors‘ abstract; BIBB-Doku)