In this thesis, we attempt to propose a strategy for discovering the contents people
are sharing inside Twitter using information visualization. Twitter is one of the most
popular social networking services nowadays which grows dramatically in recent years.
These services such as Twitter, Facebook, and MySpace are becoming more and more
important in our lives. People share information by text, image, video, etc. Thus,
by analyzing social network data, meaningful information can be discovered, such as
popular topics users are discussing, and trends of important events. But, the result
generated by data analysis is not easy for people to interpret directly. Information
visualization then becomes a key to assist user in interpreting data.
The primary goal of this work is to visualize time-varying Twitter text data by
word cloud. While the word cloud has widely been used to visualize text data, to
visualize time-varying text data there still exist many additional challenges. Therefore,
we introduce an animation-based dynamic time-varying word clouds design to
address this problem. We first propose a circular word cloud layout to provide users
an overview of the time-varying data content. Based on this layout, we propose animation
methods to assist users in interpreting the property of time-vary data. The
animated word clouds preserve the context while the focus is changing. Thus, the
visualization not only provides an overview of huge time-varying Twitter text data,
but also assists users in identifying the changing of content from time to time. Finally,
two case studies are provided. One is the visualization of a long term event,
and the other is the visualization of a series of short term events people in Twitter
were discussing.