The application may take 10-15 seconds to load the first time you use it. You may also need to click on it once to activate it depending on your browser/operating system combination.
The tool loads the latest 500 popular stories for any topic or sub-topic within Digg and analyzes the text found in the story titles and descriptions. An 'attention timeline' , tag clouds of related words, and a graph showing the number of articles that contain the various combinations of words are then displayed. You can click on a word in the association cloud to make it the primary word of interest or you can click on the main key word to enter edit mode and change the word to whatever you like. You can also click on the bars in the bar graph to show the list of stories that match the combination of words that the bar represents.
Incidentally, I'm available for data analysis or visualization projects if anybody is interested in working together. I live near Toronto, Canada but I'm open to projects done remotely. I would be happy with projects in size from a few days to a few months of work. Send me an email if you are interested.
This application requires java to run and was constructed using Processing. The folks at Digg have provided an excellent api that made it quite simple to extract the data. I'm not affiliated with Digg in any way. As always, feedback is welcome !
If you found this interesting you might like to take a look at these as well: