The Global Twitter Heartbeat -- #tweetbeat

 Videos  |  Heat Maps  |  Graphs & Charts

SGI's Big Brain Computer Powers the Global Twitter Heartbeat -- #tweetbeat

SGI has partnered with 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 to create the first ever real-time combined population, tone and geographic analysis and heat map visualization of Tweets on a SGI UV 2000, the Big Brain computer. During the Supercomputing Conference 2012, live up-to-the-moment heat maps were made available to show the sentiment on Twitter.

The Global Twitter Heartbeat project performs real-time stream processing of ten percent of Twitter's 500 million daily tweets as they are posted. The project analyzes 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 ingest to data analysis to heat map visual can easily be completed in less than a second.

The project looked at two significant recent events - Hurricane Sandy and the U.S. Presidential Election. In both events, millions of tweets were sent, making Twitter a significant platform for communicating what was happening at every moment.


Videos

Hurricane Sandy: View the Superstorm Through the Eyes of Twitter

By filtering tweets that discuss the storm, get a first hand look at how the entire country was talking about the storm as it approached, made landfall, and took its course over the U.S. eastern seaboard.
US Presidential Election 2012 on Twitter

During the U.S. Presidential Election, Twitter reported 327,452 tweets per minute as news outlets began to predict an Obama victory. President Obama's victory tweet quickly became the most-retweeted message in history, setting the record in just 22 minutes after the tweet was posted. This heat map has adjusted the color spectrum to show the intensity and location of tweets favorable to either President Barack Obama or Governor Mitt Romney over the course of Election Day, from the first polls opening to after President Obama's victory speech.
The Global Twitter Heartbeat — Analyzing real-time data on the SGI UV

Hear Kalev Leetaru discuss how he went about constructing the data analysis pipeline, ingesting, analyzing and creating the visualizations on the SGI UV 2000.
Top of Page


Heat Maps of Sentiment on Twitter

Hurricane Sandy




RED represents more Negative sentiment.
BLUE represents more Positive sentiment.
Download full resolution image (ZIP)
US Presidential Election 2012




RED represents tweets about Romney.
BLUE represents tweets about Obama.
Download full resolution image (ZIP)
US Sentiment from Live Twitter Feed




RED represents more Negative sentiment.
BLUE represents more Positive sentiment.
Download full resolution image (ZIP)
Global Sentiment from Live Twitter Feed




RED represents more Negative sentiment.
BLUE represents more Positive sentiment.
Download full resolution image (ZIP)
Top of Page


Graphs and Charts


Percentage of Tweets About
Hurricane Sandy by Day


During Hurricane Sandy, the project observed a huge increase amount of tweets discussing the weather event, as a percentage of overall tweets.
Top of Page


Credits

Kalev Leetaru, University of Illinois : http://www.kalevleetaru.com

About CIGI

The CyberInfrastructure and Geospatial Information Laboratory (CIGI, http://www.cigi.illinois.edu) at the University of Illinois at Urbana-Champaign researches and develops cutting-edge cyberinfrastructure to advance geospatial sciences and technologies. Current research covers topics such as computationally intensive spatial analysis and modeling, CyberGIS, and cyberinfrastructure-based geospatial problem-solving environments and applications. CIGI includes a number of faculty, staff, and students from multiple institutions who have diverse disciplinary expertise such as Computational and Information Sciences, Computer Science, Environmental Science and Engineering, Geography, Hydrology, and Statistics. Dr. Shaowen Wang is CIGI founder and director.

About Gnip

Gnip is the world's largest provider of public social media data, serving customers in a range of industries from social media monitoring and business intelligence to finance and government. Gnip delivers more than 100 billion social data activities each month, providing unparalleled access to data from dozens of sources including Twitter, Tumblr, WordPress, Disqus and more. For more information, email info@gnip.com or visit http://gnip.com.

Images courtesy of Kalev Leetaru and CIGI



Top of Page