All this week in the final stretch to the UK General Election 2010 I intend to collect a sample of tweets each day containing the hash tag “#ge2010”. On the day itself I might consider collecting throughout the day at regular intervals. Hopefully by the end of the week I should have a nice collection of the various clusters as they build up over the days. I am also considering text scraping the tweets at regular intervals. Or then again I could simply wait and collect the archive of textual content.
So Monday the 3rd of May 2010 generates the following image with over 800 nodes – and using the Harel-Koren Fast Multiscale alogrithm to layout the graph. (click on the image to enlarge it)