Abstract
The growing popularity and diversity of social network applications present new opportunities as well as new challenges. The resulting social networks have high value to business intelligence, sociological studies, organizational studies, epidemical studies, etc. The ability to explore and extract information of interest from the networks is thus crucial. However, these networks are often large and composed of multi-categorical nodes and edges, making it difficult to visualize and reason with conventional methods. In this paper, we show how to combine statistical methods with visualization to address these challenges, and how to arrange layouts differently to better bring out different aspects of the networks. We applied our methods to several social networks to demonstrate their effectiveness in characterizing the networks and clarifying the structures of interest, leading to new findings.
Original language | English (US) |
---|---|
Pages (from-to) | 56-64 |
Number of pages | 9 |
Journal | Social Networks |
Volume | 37 |
Issue number | 1 |
DOIs | |
State | Published - May 2014 |
All Science Journal Classification (ASJC) codes
- Anthropology
- Sociology and Political Science
- General Social Sciences
- General Psychology