Towards modeling and analysis of longitudinal social networks

Abstract

"There are various methods for handling longitudinal data in graphs and social net works, all of which have an impact on the algorithms used in data analysis. This article provides an overview of limitations, potential solutions, and unanswered questions regarding diferent temporal data schemas in social networks that are compara ble to existing techniques. Restricting algorithms to a specifc time point or layer has no efect on the results. However, when applying these approaches to a network with multiple time points, adjusted algorithms or reinterpretation becomes neces sary. Therefore, using a generic defnition of temporal networks as one graph, we aim to explore how we could analyze longitudinal social networks with centrality measures. Additionally, we introduce two new measures, 'importance' and 'change', to identify nodes with specifc behaviors. We provide case studies featuring three diferent real-world networks exhibiting both limitations and benefts of the novel approach. Furthermore, we present techniques to estimate variations in importance and degree centrality over time." (Authors' abstract, BIBB-Doku)