Nov. 14, 2012 at 4:40 PM ET
Global Twitter Heartbeat isn’t the first project to offer a nifty map illustrating what we're doing in the Twitterverse at a given point in time.
A Twitter map developed by Vertalab, for example, pinpointed where the “friendliest” and “rudest” Americans live by scanning tweets containing the phrases "Good morning," and "F--- you." Another color-coded map, noted in an issue of Cartographic Perspectives, analyzed tweets to reveal where in the U.S. Twitter profanity is worst (or best).
This latest heat map, however, offers a real-time analysis of random data via supercomputer — the SGI UV 2000 Big Brain supercomputer at the University of Illinois — to process an impressive amount of raw information very quickly. (You can see how everybody's feeling on Twitter right now by going here.)
According to the description on Global Twitter Heartbeat project’s Facebook page, it works like this:
The Global Twitter Heartbeat project performs real-time stream processing of ten percent of Twitter’s 400M daily tweets as they are posted. The project analyses every tweet to assign location (not just GPS-tagged tweets, but processing the text of the tweet itself), and tone values and then visualizes the conversation in a heat map infographic that combines and displays tweet location, intensity and tone. With SGI UV, the entire process from data analysis to heat map was produced once per second.
As you can see in this video of real-time Twitter tracking during last week’s election (below), the result is a pretty accurate picture of what’s going on in the United States at any point in time. When you hear the technorati go blah blah blah about “Big Data,” this is pretty much what they’re talking about.
In the video above, blue represents pro-Barack Obama tweets, and red is for pro-Mitt Romney tweets. Note how blue blows up big at the time President Obama gives his victory speech.
The Global Heartbeat Project, a partnership between supercomputer supplier SGI Kalev H. Leetaru of the University of Illinois and Dr. Shaowen Wang of the CyberInfrastructure and Geospatial Information (CIGI) Laboratory at the University of Illinois at Urbana-Champaign, also analyzed tweets during superstorm Sandy. Using red for negative tweets and blue for positive tweets regarding Sandy, the map reveals the mood in various areas of the U.S. as Sandy progressed up the East Coast.
Of course, these maps aren’t telling us anything we didn’t know — Obama won the election, people were really freaked out about Sandy. So what’s the point of using what SGI calls “the world's largest data-mining machine” which could “ingest the entire contents of the U.S. Library of Congress print collection in less than three seconds” to make videos to show us a bunch of pretty colors?
"This real-time data analysis approach is like having a new telescope in our hands,” project co-founder Leetaru said in a press statement. “We are just seeing the Twittersphere in this way for the first time and we're still not entirely sure how to make sense of it all and what it tells us, but it is allowing us for the first time to peer in the messy chaotic world that is the heartbeat of our society."
Which means it'll eventually be used for advertising.