Community Fabric: Visualizing communities and structure in dynamic networks. (April 2022)

• Record Type: Journal Article
• Authors: Ezell, Evan; Lim, Seung-Hwan; Anderson, David; Stewart, Robert
• Is Part Of: Information visualization. Volume 21:Number 2(2022)
• Page Start: 130
• Page End: 142
• Publication Date: 2022-04
• Subjects: Dynamic graph visualization -- information visualization -- network visualization -- community detection -- dynamic networks -- graph drawing; Information visualization -- Periodicals; 006.605
• DOI: 10.1177/14738716211056036
• Languages: English
• ISSNs: 1473-8716

Abstract

We present Community Fabric, a novel visualization technique for simultaneously visualizing communities and structure within dynamic networks. In dynamic networks, the structure of the network is continuously evolving throughout time and these underlying topological shifts tend to lead to communal changes. Community Fabric helps the viewer more easily interpret and understand the interplay of structural change and community evolution in dynamic graphs. To achieve this, we take a new approach, hybridizing two popular network and community visualizations. Community Fabric combines the likes of the Biofabric static network visualization method with traditional community alluvial flow diagrams to visualize communities in a dynamic network while also displaying the underlying network structure. Our approach improves upon existing state-of-the-art techniques in several key areas. We describe the methodologies of Community Fabric, implement the visualization using modern web-based tools, and apply our approach to three example data sets.