I'm certain you can use WordNet::Similarity to help in developing a sentiment analysis system. There are many possible ways to do this. I've included a link that will show you all the papers that have both cited WordNet::Similarity and mention "sentiment". This should give you a nice set of papers to review, and I'm sure you'll find a lot of great ideas there.

http://tinyurl.com/pr2p9ua

I know that it's very easy to include Python within a Perl program (using the Perl module Inline::Python), but I don't know enough about Python to know if you can call Perl from within it. You'll want to run this by your favorite Python experts.

Regarding the time complexity of WordNet::SenseRelate, this is addressed in Varada Kolhatkar's Master's thesis, which you can find there (check out page 29 or thereabouts).


Good luck,
Ted

On Sat, May 25, 2013 at 2:10 AM, Priyanka C <priyadio@yahoo.com> wrote:

Hi sir
Thank you sir for clearing my doubt.actually i thought of using this wn silarity for sentiment analysis. for eg to group the customer revirews into 2 categories positive and negative. so i thought i can use these wn - similarity scores ...Will it be feasible.. kindly let me knw if my idea is correct will it workout...

Also i have another doubt regarding wordsense relate. i am doing my project in python where i do pos tagging and extract adjectives.if i need to relate that word to correct wordnet sense so that i can get its corresponding sentiiwordnet score. is it easy for me to integrate ur perl program with my python...how about the time complexity in cas i need to wrk on large data

Regards



__._,_.___
Reply via web post Reply to sender Reply to group Start a New Topic Messages in this topic (3)
Recent Activity:
.

__,_._,___



--
Ted Pedersen
http://www.d.umn.edu/~tpederse