home bbs files messages ]

Forums before death by AOL, social media and spammers... "We can't have nice things"

   comp.ai      Awaiting the gospel from Sarah Connor      1,954 messages   

[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]

   Message 1,547 of 1,954   
   jackie to Ted Dunning   
   Re: clustering criterion   
   23 Oct 07 04:06:00   
   
   From: clearking@gmail.com   
      
   On Oct 18, 7:49 am, Ted Dunning  wrote:   
   > With web sessions, the best proximity data you can get (in my opinion)   
   > is derived by building user or session models and then seeing how well   
   > the model predicts other sessions.  Depending on the cardinality of   
   > your event set, you may need to use a latent variable model to deal   
   > with sparsity.  If you have only a few (hundreds, say) pages that all   
   > get pretty good traffic then you may be able to model their visits   
   > explicitly.  There are many forms of latent models possible, but the   
   > latent Dirichlet work on hidden Markov models for text clustering   
   > might be of particular interest to you.   
   >   
      
   thanks a lot. i searched the Dirichlet method but i couldn't find the   
   foundation works introducing the method. any good papers to recommend?   
      
   [ comp.ai is moderated ... your article may take a while to appear. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)   

[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]


(c) 1994,  bbs@darkrealms.ca