<?xml version='1.0' encoding='utf-8'?>
<?xml-stylesheet type="text/xsl" href="/v2/static/oai2.xsl"?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-10-14T04:11:12Z</responseDate>
  <request identifier="oai:figshare.com:article/33959156" metadataPrefix="oai_dc" verb="GetRecord">https://api.figshare.com/v2/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:figshare.com:article/33959156</identifier>
        <datestamp>2026-09-21T18:01:41Z</datestamp>
        <setSpec>category_146</setSpec>
        <setSpec>category_21</setSpec>
        <setSpec>category_24</setSpec>
        <setSpec>category_734</setSpec>
        <setSpec>category_132</setSpec>
        <setSpec>portal_5</setSpec>
        <setSpec>item_type_3</setSpec>
        <setSpec>month_year_09_2026</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"  xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:title>&lt;p&gt;Advantages and limitations of each preprocessing method, as observed in this evaluation (1,400-document Khaleej corpus; scalability figures from Section 4.8). Values are drawn from Tables 2, Tables 4–12.&lt;/p&gt;</dc:title>
          <dc:creator>Kholoud Saad Al-Saleh (25085069)</dc:creator>
          <dc:subject>Space Science</dc:subject>
          <dc:subject>Biotechnology</dc:subject>
          <dc:subject>Evolutionary Biology</dc:subject>
          <dc:subject>Biological Sciences not elsewhere classified</dc:subject>
          <dc:subject>Infectious Diseases</dc:subject>
          <dc:subject>morphological segmentation achieve</dc:subject>
          <dc:subject>match morphological variants</dc:subject>
          <dc:subject>framework provides actionable</dc:subject>
          <dc:subject>creates substantial challenges</dc:subject>
          <dc:subject>concrete preprocessor choices</dc:subject>
          <dc:subject>lucene arabic analyzer</dc:subject>
          <dc:subject>arabic text preprocessing</dc:subject>
          <dc:subject>proportionally reducing encrypted</dc:subject>
          <dc:subject>enables keyword search</dc:subject>
          <dc:subject>stemming reduces vocabulary</dc:subject>
          <dc:subject>fastest per query</dc:subject>
          <dc:subject>evaluate vocabulary size</dc:subject>
          <dc:subject>incidence matrix dsse</dc:subject>
          <dc:subject>baseline &amp;# 8212</dc:subject>
          <dc:subject>query search latency</dc:subject>
          <dc:subject>set size rather</dc:subject>
          <dc:subject>limit retrieval recall</dc:subject>
          <dc:subject>vocabulary size</dc:subject>
          <dc:subject>encrypted search</dc:subject>
          <dc:subject>search latency</dc:subject>
          <dc:subject>light stemming</dc:subject>
          <dc:subject>arabic dsse</dc:subject>
          <dc:subject>size effect</dc:subject>
          <dc:subject>retrieval precision</dc:subject>
          <dc:subject>retrieval breadth</dc:subject>
          <dc:subject>index size</dc:subject>
          <dc:subject>search quality</dc:subject>
          <dc:subject>latency persists</dc:subject>
          <dc:subject>transmission cost</dc:subject>
          <dc:subject>systematic evaluation</dc:subject>
          <dc:subject>paper presents</dc:subject>
          <dc:subject>operate successfully</dc:subject>
          <dc:subject>memory scalability</dc:subject>
          <dc:subject>khoja stemmer</dc:subject>
          <dc:subject>isri stemmer</dc:subject>
          <dc:subject>fewest documents</dc:subject>
          <dc:subject>empirical evaluation</dc:subject>
          <dc:subject>driven primarily</dc:subject>
          <dc:subject>best trade</dc:subject>
          <dc:subject>assess scalability</dc:subject>
          <dc:subject>annotated 1</dc:subject>
          <dc:subject>500 documents</dc:subject>
          <dc:description>&lt;p&gt;Advantages and limitations of each preprocessing method, as observed in this evaluation (1,400-document Khaleej corpus; scalability figures from Section 4.8). Values are drawn from &lt;a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0351281#pone.0351281.t002" target="_blank"&gt;Tables 2&lt;/a&gt;, &lt;a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0351281#pone.0351281.t004 pone.0351281.t005 pone.0351281.t006 pone.0351281.t007 pone.0351281.t008 pone.0351281.t009 pone.0351281.t010 pone.0351281.t011 pone.0351281.t012" target="_blank"&gt;Tables 4–12&lt;/a&gt;.&lt;/p&gt;</dc:description>
          <dc:date>2026-09-21T18:01:14Z</dc:date>
          <dc:type>Dataset</dc:type>
          <dc:type>Dataset</dc:type>
          <dc:identifier>10.1371/journal.pone.0351281.t013</dc:identifier>
          <dc:relation>https://figshare.com/articles/dataset/_p_Advantages_and_limitations_of_each_preprocessing_method_as_observed_in_this_evaluation_1_400-document_Khaleej_corpus_scalability_figures_from_Section_4_8_Values_are_drawn_from_Tables_2_Tables_4_12_p_/33959156</dc:relation>
          <dc:rights>CC BY 4.0</dc:rights>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
