atom feed14 messages in org.apache.lucene.mahout-userRe: Automatically extracted Mahout FAQs
FromSent OnAttachments
Stefan HenßFeb 22, 2011 8:03 pm 
Stefan HenßFeb 22, 2011 9:14 pm 
Bruce DouFeb 22, 2011 9:25 pm 
Sean OwenFeb 23, 2011 12:28 am 
Isabel DrostFeb 23, 2011 5:07 am 
Ted DunningFeb 23, 2011 9:09 am 
Ted DunningFeb 23, 2011 9:34 am 
Stefan HenßFeb 23, 2011 10:52 pm 
Bruce DouFeb 23, 2011 11:11 pm 
Stefan HenßFeb 23, 2011 11:57 pm 
Stefan HenßFeb 24, 2011 12:36 am 
Stefan HenßMar 7, 2011 2:51 am 
Stefan HenßJun 9, 2011 1:16 pm 
Lance NorskogJun 10, 2011 6:16 pm 
Subject:Re: Automatically extracted Mahout FAQs
From:Ted Dunning (ted.@gmail.com)
Date:Feb 23, 2011 9:09:17 am
List:org.apache.lucene.mahout-user

I think you would get further if you used the identities of the poster. That would let you build an authoritativeness score as well as augment your topic models.

It would also be helpful to build a model that can find helpful answers based on the responses to the answer. Ken Krugler showed a simple version of this in his HUG talk starting on roughly slide 9:

http://www.slideshare.net/sh1mmer/the-bixo-web-mining-toolkit

<http://www.slideshare.net/sh1mmer/the-bixo-web-mining-toolkit>(please ignore the final scores so that I don't have to blush)

On Tue, Feb 22, 2011 at 9:15 PM, Stefan Henß <stef@googlemail.com>wrote:

- Build categorization solely based on the conversation's texts (by clustering).