Publication Date

Fall 2020

Degree Type

Master's Project

Degree Name

Master of Science (MS)


Computer Science

First Advisor

Katerina Potika

Second Advisor

Teng Moh

Third Advisor

Kevin Smith


Networks, Visualization, Graph Drawing, Community Detec- tion, Louvain, Node Size, Graph Layout, Labeling, Edge Coloring, Inter- activity


Networks show relationships between people or things. For instance, a person has a social network of friends, and websites are connected through a network of hyperlinks. Networks are most commonly represented as graphs, so graph drawing becomes significant for network visualization. An effective graph drawing can quickly reveal connections and patterns within a network that would be difficult to discern without visual aid. But graph drawing becomes a challenge for large networks. Am- biguous edge crossings are inevitable in large networks with numerous nodes and edges, and large graphs often become a complicated tangle of lines. These issues greatly reduce graph readability and makes analyzing complex networks an arduous task. This project aims to address the large network visualization problem by com- bining recursive community detection, node size scaling, layout formation, labeling, edge coloring, and interactivity to make large graphs more readable. Experiments are performed on five known datasets to test the effectiveness of the proposed approach. A survey of the visualization results is conducted to measure the results.