Detecting Stable Communities in Link Streams at Multiple Temporal Scales

Abstract

Link streams model interactions over time in a wide range of fields. Under this model, the challenge is to mine efficiently both temporal and topological structures. Community detection and change point detection are one of the most powerful tools to analyze such evolving interactions. In this paper, we build on both to detect stable community structures by identifying change points within meaningful communities. Unlike existing dynamic community detection algorithms, the proposed method is able to discover stable communities efficiently at multiple temporal scales. We test the effectiveness of our method on synthetic networks, and on high-resolution time-varying networks of contacts drawn from real social networks.

Homophilic and Heterophilic Characteristics Shaping Community Formation in Human Mobility Networks During Extreme Weather Response

“…In this study, we adopted the community detection algorithm developed by Boudebza et al (2020) to identify communities in human mobility networks during Winter Storm Uri in February 2021. The human mobility data was obtained from Spectus to construct networks of human movements among spatial areas.…”

“…Qin et al (2020) proposed a density-based clustering algorithm to detect stable communities over time in a dynamic graph. In this paper, we used the algorithm proposed by Boudebza et al (2020), a link stream-based approach, to detect stable communities at multiple temporal scales without redundancy instead of choosing an arbitrarily temporal scale and to perform temporal community detection on all time steps in parallel.…”