Mapping the Conversation:

Political Topics and Geography on Twitter

Twitter has grown to become an important aspect of public debate and leading up to Tuesday's midterms; the Twitterverse is abuzz with conversations on the topics that will help decide the individual races.

It is well-known that the state you live in plays a role in deciding what issues you care about. By utilizing the fact that conversations on Twitter are public, we can geocode individual tweets, and study where Americans are talking about specific issues.

In this way, Twitter allows us to extrapolate from millions of water cooler conversations and show where the conversations are taking place right now. The resulting maps are displayed below:

 

 

Standard representationArea cartogram representation
 
Time showed (drag slider below to change):  loading...

(As of loading.... Intensity of color corresponds to fraction of tweets on the selected topic. Click to refresh.)

In Video Format

Below are static videos for each of the keywords, as measured on November 1st, 2010.

About the Issues

Each of the keywords above arises from a set "issues" generated by mining the full set of candidates' campaign web sites. Our keywords are

About the Data and Visualization

The plots are calculated using the live "gardenhose" Twitter stream, and represented as density-preserving cartograms. Each cartogram covers a two-hour period ending at the time stated. County area data were taken from the U.S. Census Bureau, and the base U.S. map was taken from Wikimedia Commons. User locations were inferred using the Google Maps API, and mapped into counties using PostGIS and U.S. county maps from the U.S. National Atlas. Colors were selected using Color Brewer 2.

About Cartograms

An area cartogram is a map in which the mapping variable (in this case, the number of tweets) is substituted for the true land area. Thus, the geometry of the actual map is altered so that the shape of each region is maintained as much as possible, but the area is scaled in order to be proportional to the number of tweets that originate in that region. The result is a density-equalizing map. The cartograms in this work were generated using the cart software by Mark E. J. Newman, available at http://www-personal.umich.edu/~mejn/cart.

Who We Are

We are researchers from Northeastern University and Harvard University, studying the characteristics and dynamics of Twitter. This research is made possible by an Amazon Web Services in Research Grant.

© 2010 Alan Mislove, Sune Lehmann, Yong-Yeol Ahn, David Lazer, Yuru Lin, Jukka-Pekka Onnela, J. Niels Rosenquist. Some rights reserved. Images, poster, and movie are shared under the Creative Commons Attribution 3.0 License.