Journal article
Modeling shared e-micromobility as a label propagation process for detecting overlapping communities
Computers, environment and urban systems, Vol.122, p.102336
12/2025
DOI: 10.1016/j.compenvurbsys.2025.102336
Abstract
Shared micro-mobility such as electric scooters (e-scooters) has gained significant popularity in many cities. While many studies have analyzed the spatiotemporal patterns of shared micro-mobility using individual-level trip data, the spatial structure of e-scooter mobility networks and their socio-economic implications remain underexplored. Examining these mobility networks through the lens of network science — such as analyzing their community structures — can provide valuable insights for urban policy and planning. For example, allocating e-scooters at the overlapping locations of two communities may improve the operational efficiency of e-scooter distribution. However, existing methods for detecting community structures in mobility networks often overlook potential overlaps between communities. In this study, we conceptualize shared micro-mobility in urban spaces as a process of information exchange, where locations are connected through e-scooters, facilitating the interaction and propagation of community affiliations. As a result, similar locations are assigned the same label. Based on this concept, we developed a Geospatial Interaction Propagation model (GIP) by designing a Speaker-Listener Label Propagation Algorithm (SLPA) that accounts for geographic distance decay, incorporating anomaly detection to ensure the derived community structures reflect meaningful spatial patterns.We applied this model to detect overlapping communities within the e-scooter system in Washington, D.C. The results demonstrate that our algorithm outperforms existing model of overlapping community detection in both efficiency and modularity. Additionally, we discovered significant social segregation within the overlapping communities: areas belong to multiple communities tend to be wealthier with shorter commute times. Our results provide a potential explanation for the community structure in human mobility networks and may offer insights for urban planning and policymaking aimed at creating a more equitable and accessible mobility system.
•Human mobility is modeled as a geographically constrained speaker–listener process.•The model uses anomaly detection to extract overlapping communities with spatial structure.•Applied to Washington D.C. e-scooters, marking the first discovery of overlapping micromobility groups.•Overlapping communities cluster in wealthy, predominantly white areas with short commutes.
Details
- Title: Subtitle
- Modeling shared e-micromobility as a label propagation process for detecting overlapping communities
- Creators
- Peng Luo - Massachusetts Institute of TechnologyChengyu Song - University of AlabamaHao Li - National University of SingaporeDi Zhu - University of MinnesotaSonghua Hu - Massachusetts Institute of TechnologyFábio Duarte - Massachusetts Institute of Technology
- Resource Type
- Journal article
- Publication Details
- Computers, environment and urban systems, Vol.122, p.102336
- DOI
- 10.1016/j.compenvurbsys.2025.102336
- ISSN
- 0198-9715
- eISSN
- 1873-7587
- Publisher
- Elsevier Ltd
- Language
- English
- Date published
- 12/2025
- Academic Unit
- School of Earth, Environment, and Sustainability
- Record Identifier
- 9985219852802771
Metrics
1 Record Views