Exploring the raison d’etre behind metric selection in network analysis: a systematic review

Abstract

Network analysis is a useful tool to analyse the interactions and structure of graphs that represent the relationships among entities, such as sectors within an urban system. Connecting entities in this way is vital in understanding the complexity of the modern world, and how to navigate these complexities during an event. However, the field of network analysis has grown rapidly since the 1970s to produce a vast array of available metrics that describe different graph properties. This diversity allows network analysis to be applied across myriad research domains and contexts, however widespread applications have produced polysemic metrics. Challenges arise in identifying which method of network analysis to adopt, which metrics to choose, and how many are suitable. This paper undertakes a structured review of literature to provide clarity on raison d’etre behind metric selection and suggests a way forward for applied network analysis. It is essential that future studies explicitly report the rationale behind metric choice and describe how the mathematics relates to target concepts and themes. An exploratory metric analysis is an important step in identifying the most important metrics and understanding redundant ones. Finally, where applicable, one should select an optimal number of metrics that describe the network both locally and globally, so as to understand the interactions and structure as holistically as possible.

Molecular insights into the anti‐inflammatory activity of fermented pineapple juice using multimodal computational studies

“…This metric helps evaluate the complexity and interconnectedness of the network. [ 41 ] Additionally, the betweenness centrality, a measure of how often a target acts as a bridge connecting other targets in the network, [ 42 ] was calculated. The median value of the betweenness centrality was determined to be 0.003.…”

The Relationship of Corporate Social Responsibility with Business Performance—A Bibliometric Literature Review

“…SLNA was chosen because it deploys strict procedures in the search and selection of publications for a synthesis of what various studies have shown and how they have impacted policy and practice over time [19]. SLNA is also widely acknowledged for its objectivity in and suitability for identifying research trends and networks of relationships among authors, in enhancing an understanding of the current state of the research in any field and in identifying the gaps in the research, as well as areas of improvement [20].…”

Using Complex Networks in the Hearing Sciences

“…Once a system has been represented as a complex network, various measures of the network structure and organization can then be made at the micro-level to examine individual nodes, at the macro-level to examine the overall structure of the whole network, or the meso-level to examine subsets of nodes in the whole network (Morrison et al 2022). The structure of the complex network is important to understand, because the way in which a network is organized can influence processing in that system (Kleinberg 2000).…”