<?xml version="1.0" encoding="UTF-8"?>
<posts update='2008-07-09 19:47:38' user=""><post 
   href="http://www.dbsight.net/" 
   description="DBSight: Instant Scalable Full-text database search platform/engine" 
   
     extended="ght also has statis" 
   
   hash="9d5744190d4fc6c8fdf7cdcd5f474b58"
   user="hotho"
   tag="database engine integration lucene search text "
   time="2008-05-22T15:08:44+0200" />
<post 
   href="http://people.csail.mit.edu/jrennie/20Newsgroups/" 
   description="Home Page for 20 Newsgroups Data Set" 
   
     extended="The 20 Newsgroups data set" 
   
   hash="bbb84b0f8c4f9921aaa40e1a07190279"
   user="hotho"
   tag="20 dataset newsgroups text "
   time="2008-04-12T15:32:30+0200" />
<post 
   href="http://kdd.ics.uci.edu/databases/20newsgroups/20newsgroups.html" 
   description="20 Newsgroups" 
   
     extended="20 Newsgroups 


 Abstract
This data set consists of 20000 messages taken from 20 Usenet newsgroups.

 Information files:


    description of the data 


 Data files:


    20_newsgroups.tar.gz (17.3M; 61.6M uncompressed)
    mini_newsgroups.tar.gz A subset composed of 100 articles from each newsgroup. (1.9M; 6.2M uncompressed)" 
   
   hash="6ee032e41e462edbe7baf2db309d0370"
   user="hotho"
   tag="20 dataset newsgroups text "
   time="2008-04-12T15:32:12+0200" />
<post 
   href="http://www.data-miner.com/" 
   description="Predictive Data Mining and Text Mining Software" 
   
     extended="Software can be downloaded by using:
l: tmskriktext
p: 780387954332" 
   
   hash="0d682a4e40aa9800f9e1a77525ac506e"
   user="hotho"
   tag="dm mining software text tm "
   time="2008-04-12T15:17:18+0200" />
<post 
   href="http://www.semantichacker.com/" 
   description="SemanticHacker" 
   
   hash="fc3d400ffc6b736a3e4cdbe533263ffc"
   user="hotho"
   tag="challenge nlp prize semantic text "
   time="2008-03-20T08:36:25+0100" />
<post 
   href="http://mlkd.csd.auth.gr/multilabel.html" 
   description="Multilabel Classification" 
   
     extended="Multi-Label Classification" 
   
   hash="ca1734ab575c5ca632a28d7b59aa4d5b"
   user="hotho"
   tag="classification dataset extension multilabel text tools weka "
   time="2007-11-23T13:12:59+0100" />
<post 
   href="http://aune.lpl.univ-aix.fr/projects/multext/" 
   description="Multext" 
   
   hash="aadc8b8fde1c4cc4affcfa02f649f6be"
   user="hotho"
   tag="corpus dataset text "
   time="2007-11-16T17:36:20+0100" />
<post 
   href="http://datamining.typepad.com/" 
   description="Data Mining: Text Mining, Visualization and Social Media" 
   
   hash="5418a3c201e679ea63e31a9089541698"
   user="hotho"
   tag="blog data dm mining ml social text tm toread "
   time="2007-10-28T15:47:38+0100" />
<post 
   href="http://www.ebi.ac.uk/citexplore/" 
   description="CiteXplore" 
   
     extended="CiteXplore combines literature search with text mining tools for biology.
                                    Search results are cross referenced to EBI applications based on publication identifiers. 
                                    Links to full text versions are provided where available." 
   
   hash="56bc9f4ee22c3b90963c62eb673118c4"
   user="hotho"
   tag="Literatur citeseer database full literature search suche text "
   time="2007-10-19T22:21:08+0200" />
<post 
   href="http://www.olaf-schultz.com/lieder/probiersmal.pdf" 
   description="Dschungel Buch - Probiers mal mit Gemütlichkeit" 
   
   hash="e7238e0c27fecc8b1dd724efd044419e"
   user="hotho"
   tag="Dschungelbuch noten text "
   time="2007-05-27T10:57:00+0200" />
</posts>
