CommViz: Visualization of semantic patterns in large social communication networks

Abstract

We introduce CommViz, an information visualization tool that enables complex communication networks to be explored, exposing trends and patterns in the data at a glance. We adapt a visualization approach known as hive plots to reflect the semantic structure of the networks, a generalization we call semantic hive plots. The method efficiently organizes and provides insight into complex, high-dimensional communication data such as email and messages on social media. We present the architecture of the CommViz tool and its application to the Enron email corpus as a case study, demonstrating how the structure of the visualization enables investigation of patterns and relationships in a large set of messages. We also provide a user study performed with Amazon Mechanical Turk that shows the value of the tool for certain complex data interrogations and further show how the incorporation of semantic structure on semantic coordinates can also be applied to parallel coordinates visualization. The integration of the social network characteristics with semantic attributes of the underlying data in a single visualization is, to our knowledge, a novel contribution of the work. The tool can be accessed atWe present CommViz, an approach to supporting analysts who are struggling to gain insight into the patterns of communication in complex message data sets. As data sets increase in size and complexity, it becomes increasingly challenging to extract information from them. Visual representations of data can provide a means for users to analyze and reason about the content of data sets, making use of the power of the human perceptual system. 1 Such representations are most effective when they are interpretable and reflect the analytic tasks that the analysts perform.CommViz makes use of existing structure in social communication network data such as email, instant messaging or online forums-utilizing metadata associated with each individual message indicating the sender, recipient(s), and the date and time of message transmission-and couples that structure with further contextual attributes, such as the inferred thematic content (topic) of the messages or the location of the sender. This allows an analyst using the tool to easily answer questions such as ''Who sent a message to Whom in What context?'' and to visually observe patterns in the data, such as hot topics, the most active communicators, and periods of intense message activity. It has applications in a range of contexts, including business intelligence, disaster management coordination, and law enforcement.The tool encompasses several innovations:The adaptation of a visualization approach called hive plots, originally developed for biological network visualization, 2 to enable clear expression of communication network structure. The novel contribution of this adaptation is to plot the data in terms of the data semantics rather than the quantitative characteristics of the network structure. We therefore call the adaptation semantic hive plots.The incorporation of an addition...

Exploring the limits of complexity: A survey of empirical studies on graph visualisation

“…Most studies use graphs with densities of 50% or less. There are only three studies that use graphs with densities higher than 50% [58,129,141]. All three studies evaluate methods that are tailored to scale well for dense networks.…”

“…There are only 28 studies that use graphs with 1,000 edges or more. Most of these allow the participants to look at parts of the network instead of performing the task on the whole network [12,37,52,56,82,85,88,94,95,99,101,102,117,120,124,129,132,136,146,152]. Similar to studies that use a large number of nodes to highlight the benefits of aggregation or interaction methods, some studies use a large number of edges to show the benefits of edge compression, bundling, or highlighting techniques.…”