Final project for Visualizing Literature independent study.
When I started this, I was honestly stumped about what I wanted to do for it. I knew that what I had to do should include some form of part-of-speech tagging, and probably some usage of Wordnet as well, but I wasn't sure how to incorporate both.
What it eventually came down to was this: what I find most fascinating about books are the characters. So I decided that characters would be my focus. I realized that I could use part-of-speech tagging to find adjectives associated with the characters, even if the method I used (finding all adjectives in the same sentence as a character's name) wasn't necessarily the best way of going about it. The next thing I did was used a frequency distribution to figure out which adjective was used the most for each character. The last stage was to use Wordnet to find all of the synonyms of that word.
Originally what I wanted to do was have some way of visualizing character similarities - i.e. if two characters shared the same adjective, I wanted to show it. I have yet to figure out how to do this, but I'm still fairly happy with the result, which is that a viewer can look at each major character in Dracula and figure out what they're like (or what fate they had) based on the words surrounding them.
You can find the final product here: http://web.engr.illinois.edu/~spratle2/mp3.html