Interactive Visual Analysis of High Throughput Text Streams
Chad A. Steed, Thomas E. Potok, Robert M. Patton, John R. Goodall, Christopher S Maness, James K Senter · 2012
The scale, velocity, and dynamic nature of large scale social media systems like Twitter demand a new set of visual analyt-ics techniques that support near real-time situational aware-ness. Social media systems are credited with escalating so-cial protest during recent large scale riots. Virtual commu-nities form rapidly in these online systems, and they occa-sionally foster violence and unrest which is conveyed in the users ’ language. Techniques for analyzing broad trends over these networks or reconstructing conversations within small groups have been demonstrated in recent years, but state-of-the-art tools are inadequate at supporting near real-time anal-ysis of these high throughput streams of unstructured infor-mation. In this paper, we present an adaptive system to dis-cover and interactively explore these virtual networks, as well as detect sentiment, highlight change, and discover spatio-temporal patterns. Author Keywords Visual analytics; text analytics; stream analysis; visualization; sentiment analysis; change detection; social media; geospatial; temporal.