<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta>
      <journal-title-group>
        <journal-title>March</journal-title>
      </journal-title-group>
    </journal-meta>
    <article-meta>
      <title-group>
        <article-title>But where do we go from here?</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <string-name>Ian Ruthven</string-name>
          <email>ian.ruthven@cis.strath.ac.uk</email>
          <xref ref-type="aff" rid="aff0">0</xref>
        </contrib>
        <aff id="aff0">
          <label>0</label>
          <institution>University of Strathclyde Department of Computer and Information Sciences</institution>
        </aff>
      </contrib-group>
      <pub-date>
        <year>2010</year>
      </pub-date>
      <volume>28</volume>
      <issue>2010</issue>
      <abstract>
        <p />
      </abstract>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>Contextual information retrieval has promised much and has
produced interesting ideas and new systems developments.
Although there has been much discussion on the evaluation
of context-free information retrieval systems, there has been
far less discussion on the challenges of evaluating contextual
systems.</p>
      <p>In this presentation I will step back from the debates
about speci c methodologies to argue for approaches that
acknowledge the context of use of IR systems and the
context of information itself. I shall pose some challenges for
contextual IR evaluation based on the context in which our
systems are deployed in real-life situations and give a
personal view on some useful evaluation directions.</p>
    </sec>
  </body>
  <back>
    <ref-list />
  </back>
</article>