Hi
I remember doing it once a long time ago (Lucene 1.9) but could not go
anywhere since term vectors and such were not easily accessible then.
However, if text analytics is what you are after, perhaps you already
know about LingPipe. I used it for named entity extraction (enhanced
with some TF-IDF statistical information from Lucene Index) and it
worked well.
Maybe, you can do the same for sentiment analysis i.e. use LingPipe
capabilities but enhance it with the corpus statistics that the Lucene
index provides - and which are more powerful now.
HTH,
Srikant
Aaron Schon 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
----------------------------------------------------------------------
Find out how you can get spam free email.
http://www.bluebottle.com/tag/3
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
