0

I am trying to find blog posts/research articles relating to using the NLTK library in fiction/philosophy analysis. I am entirely new to this - although not new to programming.

I've seen things relating to text classification and sentiment analysis, but not many that does something similar to what this article does : Fictional Simulation, Automatic Extraction of Key Scenes from Novels

In order to get a feeling with what NLTK enables us to do, I've built a small program that takes a text, split it in three parts, takes the 10 most frequent words of the first part and looks at the evolution of the context in which these words are used in the two other parts. Does that make any sense?

If you know of a good NLTK community, I would be happy to know - I tried IRC but the channel seems quiet...

Thank you and have a wonderful day !

PS : I do not know how to avoid being flag since this isn't a straight Q&A answer, but felt that this question had the most chance of being answered here.

abourbaki
  • 67
  • 7
  • 3
    Sorry, I think your question will be closed soon :( Have you seen this mailing list? https://groups.google.com/forum/#!forum/nltk-users That may be your best bet. If you have a more specific nltk question (with code demonstrating the problem you're facing) you may have better luck here on SO. – Steven Kryskalla Aug 09 '15 at 17:20
  • @StevenKryskalla : thank you! :) I will try posting it there also. – abourbaki Aug 09 '15 at 17:26
  • some useful tips: try eliminating stop words before getting frequent words. see http://stackoverflow.com/questions/5486337/how-to-remove-stop-words-using-nltk-or-python . Also there is an information content theory that says least frequent words are more important. I suggest you look at http://www.aclweb.org/anthology/ you can find very good papers on every possible nlp categories. – maanijou Aug 17 '15 at 10:05

0 Answers0