Database Reference
In-Depth Information
Chapter 5
Visualizing Twitter Data
When users interact on Twitter, network information is generated, and when they
publish Tweets, textual information is generated. Tweets themselves have other
embedded information, such as location information. In addition, users have profiles
where they describe themselves through fields, such as their name and website.
Visualization techniques can help us efficiently analyze and understand how and
why users interact on Twitter. In this chapter, we discuss techniques to create
visualizations for the four types of information: network, temporal, geospatial, and
textual information. While discussing the techniques, we follow the visualization
mantra: “Overview first, then zoom and filter. Details on demand” [
4
].
5.1
Visualizing Network Information
In the previous chapter, we discussed network measures to identify important people
and concepts in the network. In this section, we will continue that discussion and
present a technique to visualize a network to gain insight into how and why users
interact. We will focus our discussion on two types of networks:
Information flow networks, and
Friend-Follower networks.
Below, we discuss each type of networks in detail and provide an example
to illustrate the unique aspects of the network and how visualization can help in
understanding them.
5.1.1
Information Flow Networks
On Twitter, information spreads primarily through retweeting. The resulting Tweet
is called a retweet. When we visualize retweets we are essentially visualizing the
flow of information in the network. In the previous chapter, we discussed centrality
