The Human-Computer Interaction Lab, University of Maryland, presents an interesting OpenLaszlo application for analyzing word frequency in a document (via David Temkin).


click to interact with FeatureLens

It took a bit of poking around to figure out where to start and what to do with this app. (You want to click the “load” button in the upper right.) I explored the “State of the Union” a bit…

Initially, we can see the frequency of words in the speech:

I also looked at words which decrease in frequency throughout the document. By selecting “budget” you can see a graph of how often that word is used through the course of the speech:

In looking at words that increase in frequency, we can see that “Iraq” is discussed more toward the end of the speech:

The selection of trends in the distribution of pattern frequencies allows collecting meaningful pieces of information about the text. FeatureLens is a “provocational” tool as it gives rise to new questions and hypotheses, as well as insights about the text.

What do you think?