If you're new to NLP, I recommend getting a book like Natural Language
Processing with Python, using the Python Twitter API, and writing a Bayesian
spam classifier. If you're less new, I've been working in sentiment
classification for a while now and it's a lot of fun. Also things like
automatically grouping tweeters by topic, or scanning someone's tweets to
see if you should follow them, can be cool projects.

j

On Sun, Feb 28, 2010 at 10:16 PM, Bryan <k0...@dbbear.com> wrote:

> Google: Latent Semantic Analysis, Latent Relational Analysis, and
> Vector Space Model
>
> Check out the book: Algorithms of the Intelligent Web from Manning:
> http://www.manning.com/marmanis/
>
> I've blogged a bit about some of the things I applied to Twitter at:
> http://skimmeragent.blogspot.com/
>
> Good luck.
>
> Bryan
>

Reply via email to