I will be getting all the text data(ebooks) from gutenberg project ( http://www.gutenberg.org/). I plan to use 100 ebooks and classify them.Romance, horror, fantasy, politics are the main genre of books i am looking for, i wanted to have thriller in my list but the keyword occurrences in horror and thriller are very much similar which wouldn`t have given clear results in the end . Feeding the data and manipulating (converting it into Vector space models) it so that it can be used for affect recognition will be an issue. I plan to take Mac Kims help on this, as he has already done research in this area.
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment