Thanks to those who responded. I was wondering if taking a bag of words 
approach might work. For example chunking the sentences to be analyzed and 
running a Lucene query against an index storing sentiment polarity. Has anyone 
had success with this approach? I do not need a super accurate system, 
something that is "reasonably" accurate.

Also, could you suggest good publicly available training datasets? I am aware 
of the Cornell Movie Reviews dataset[1]

Thanks
AS

[1] http://www.cs.cornell.edu/people/pabo/movie-review-data/


----- Original Message ----
From: Vivek Balaraman <[EMAIL PROTECTED]>
To: java-user@lucene.apache.org
Sent: Saturday, March 1, 2008 6:35:04 AM
Subject: Re: Lucene for Sentiment Analysis

We've been working on Sentiment Analysis. We use GATE and Wordnet for the
lexical / semantic analysis and J Free Charts for the visualization. The
domain is reviews on retail banking and in general our accuracy is around
75% and recall around 25%

We tried out lingpipe as well which also gave good results.

Tx
Vivek Balaraman


On Sat, Mar 1, 2008 at 3:16 AM, Aaron Schon <[EMAIL PROTECTED]> wrote:

> Hello, I was interested to learn about using Lucene for text analytics
> work such as for Sentiment Analysis. Has anyone done work along these lines?
> if so, could you share your approach, experiences, accuracy levels obtained
> etc.
>
> Thanks,
> AS
>
>
>
>  
> ____________________________________________________________________________________
> Looking for last minute shopping deals?
> Find them fast with Yahoo! Search.
> http://tools.search.yahoo.com/newsearch/category.php?category=shopping
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: [EMAIL PROTECTED]
> For additional commands, e-mail: [EMAIL PROTECTED]
>
>


      
____________________________________________________________________________________
Be a better friend, newshound, and 
know-it-all with Yahoo! Mobile.  Try it now.  
http://mobile.yahoo.com/;_ylt=Ahu06i62sR8HDtDypao8Wcj9tAcJ 


---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]

Reply via email to