<?xml version="1.0"?>

<!DOCTYPE owl [
  <!ENTITY rdf "http://www.w3.org/1999/02/22-rdf-syntax-ns#">
  <!ENTITY rdfs "http://www.w3.org/2000/01/rdf-schema#">
  <!ENTITY xsd "http://www.w3.org/2001/XMLSchema#">
  <!ENTITY owl "http://www.w3.org/2002/07/owl#">
  <!ENTITY cc "http://web.resource.org/cc/#">
  <!ENTITY project "http://ebiquity.umbc.edu/ontology/project.owl#">
  <!ENTITY person "http://ebiquity.umbc.edu/ontology/person.owl#">
  <!ENTITY pub "http://ebiquity.umbc.edu/ontology/publication.owl#">
  <!ENTITY assert "http://ebiquity.umbc.edu/ontology/assertion.owl#">]>

<!--
  This ontology document is licensed under the Creative Commons
  Attribution License. To view a copy of this license, visit
  http://creativecommons.org/licenses/by/2.0/ or send a letter to
  Creative Commons, 559 Nathan Abbott Way, Stanford, California
  94305, USA.
-->

<rdf:RDF 
  xmlns:rdf = "&rdf;"
  xmlns:rdfs = "&rdfs;"
  xmlns:xsd = "&xsd;"
  xmlns:owl = "&owl;"
  xmlns:cc = "&cc;"
  xmlns:project = "&project;"
  xmlns:person = "&person;"
  xmlns:pub = "&pub;"
  xmlns:assert = "&assert;">
  <pub:InProceedings rdf:about="http://ebiquity.umbc.edu/paper/html/id/460/Improving-Binary-Classification-on-Text-Problems-using-Differential-Word-Features">
    <rdfs:label><![CDATA[Improving Binary Classification on Text Problems using Differential Word Features]]></rdfs:label>
    <pub:title><![CDATA[Improving Binary Classification on Text Problems using Differential Word Features]]></pub:title>
    <pub:publishedOn rdf:datatype="&xsd;dateTime">2009-11-02T00:00:00-05:00</pub:publishedOn>
    <pub:abstract><![CDATA[We describe an efficient technique to weigh word-based features in binary classification tasks and show that it significantly improves classification accuracy on a range of problems. The most common text classification approach uses a document's ngrams (words and short phrases) as its features and assigns feature values equal to their frequency or TFIDF score relative to the training corpus. Our approach uses values computed as the product of an ngram's document frequency and the difference of its inverse document frequencies in the positive and negative training sets. While this technique is remarkably easy to implement, it gives a statistically significant improvement over the standard bag-of-words approaches using support vector machines on a range of classification tasks.  Our results show that our technique is robust and broadly applicable. We provide an analysis of why the approach works and how it can generalize to other domains and problems.

<p>
<i>This is a preprint of a short (poster) paper to appear in the Proceedings of the 18th ACM Conference on Information and Knowledge Management, Hong Kong, 2-6 November 2009.</i></p?


]]></pub:abstract>
    <pub:counter>1413</pub:counter>
    <pub:googleKey>q7_Ee-QysQIJ</pub:googleKey>
    <pub:googleCitations>4</pub:googleCitations>
    <pub:tag><![CDATA[text classification]]></pub:tag>
    <pub:tag><![CDATA[learning]]></pub:tag>
    <pub:tag><![CDATA[sentiment]]></pub:tag>
    <pub:tag><![CDATA[natural language processing]]></pub:tag>
    <pub:tag><![CDATA[natural language processing]]></pub:tag>
    <pub:tag><![CDATA[learning]]></pub:tag>
    <pub:booktitle><![CDATA[Proceedings of the 18th ACM Conference on Information and Knowledge Management]]></pub:booktitle>
    <pub:publisher><![CDATA[ACM Press]]></pub:publisher>
    <pub:author>
       <rdf:List>
         <rdf:first><person:PhDStudent rdf:about="http://ebiquity.umbc.edu/person/html/Justin/Martineau/"><person:name><![CDATA[Justin  Martineau]]></person:name><rdfs:label><![CDATA[Justin  Martineau]]></rdfs:label></person:PhDStudent></rdf:first>
         <rdf:rest>
           <rdf:List>
             <rdf:first><person:PrincipalFaculty rdf:about="http://ebiquity.umbc.edu/person/html/Tim/Finin/"><person:name><![CDATA[Tim  Finin]]></person:name><rdfs:label><![CDATA[Tim  Finin]]></rdfs:label></person:PrincipalFaculty></rdf:first>
             <rdf:rest>
               <rdf:List>
                 <rdf:first><person:PrincipalFaculty rdf:about="http://ebiquity.umbc.edu/person/html/Anupam/Joshi/"><person:name><![CDATA[Anupam  Joshi]]></person:name><rdfs:label><![CDATA[Anupam  Joshi]]></rdfs:label></person:PrincipalFaculty></rdf:first>
                 <rdf:rest>
                   <rdf:List>
                     <rdf:first><person:BSStudent rdf:about="http://ebiquity.umbc.edu/person/html/Shamit/Patel/"><person:name><![CDATA[Shamit  Patel]]></person:name><rdfs:label><![CDATA[Shamit  Patel]]></rdfs:label></person:BSStudent></rdf:first>
                     <rdf:rest rdf:resource="&rdf;nil" />
                   </rdf:List>
                 </rdf:rest>
               </rdf:List>
             </rdf:rest>
           </rdf:List>
         </rdf:rest>
       </rdf:List>
    </pub:author>
    <pub:firstAuthor><person:PhDStudent rdf:about="http://ebiquity.umbc.edu/person/html/Justin/Martineau/"><person:name><![CDATA[Justin  Martineau]]></person:name><rdfs:label><![CDATA[Justin  Martineau]]></rdfs:label></person:PhDStudent></pub:firstAuthor>
    <pub:softCopy><pub:SoftCopy>
      <pub:softCopyFormat><![CDATA[PDF Document]]></pub:softCopyFormat>
      <pub:softCopyURI><![CDATA[http://ebiquity.umbc.edu/get/a/publication/461.pdf]]></pub:softCopyURI>
      <pub:softCopySize>103482</pub:softCopySize>
    </pub:SoftCopy></pub:softCopy>
    <pub:softCopy><pub:SoftCopy>
      <pub:softCopyFormat><![CDATA[Microsoft PowerPoint]]></pub:softCopyFormat>
      <pub:softCopyURI><![CDATA[http://ebiquity.umbc.edu/get/a/publication/470.ppt]]></pub:softCopyURI>
      <pub:softCopySize>1876480</pub:softCopySize>
    </pub:SoftCopy></pub:softCopy>
  </pub:InProceedings>

  <rdf:Description rdf:about="">
    <cc:License rdf:resource="http://creativecommons.org/licenses/by/2.0/" />
  </rdf:Description>

</rdf:RDF>

