<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>1870-9044</journal-id>
<journal-title><![CDATA[Polibits]]></journal-title>
<abbrev-journal-title><![CDATA[Polibits]]></abbrev-journal-title>
<issn>1870-9044</issn>
<publisher>
<publisher-name><![CDATA[Instituto Politécnico Nacional, Centro de Innovación y Desarrollo Tecnológico en Cómputo]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S1870-90442016000100043</article-id>
<article-id pub-id-type="doi">10.17562/PB-53-4</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[A Segment-based Weighting Technique for URL-based Genre Classification of Web Pages]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Jebari]]></surname>
<given-names><![CDATA[Chaker]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,College of Applied Sciences  ]]></institution>
<addr-line><![CDATA[Ibri ]]></addr-line>
<country>Sultanate of Oman</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>06</month>
<year>2016</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>06</month>
<year>2016</year>
</pub-date>
<numero>53</numero>
<fpage>43</fpage>
<lpage>47</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_arttext&amp;pid=S1870-90442016000100043&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_abstract&amp;pid=S1870-90442016000100043&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_pdf&amp;pid=S1870-90442016000100043&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract: We propose a segment-based weighting technique for genre classification of web pages. This technique exploits character n-grams extracted from the URL of the web page rather than its textual content. The main idea of our technique is to segment the URL and assigns a weight for each segment. Experiments conducted on three known genre datasets show that our method achieves encouraging results.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[URL]]></kwd>
<kwd lng="en"><![CDATA[genre classification]]></kwd>
<kwd lng="en"><![CDATA[web page]]></kwd>
<kwd lng="en"><![CDATA[segment weight]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Baykan]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Henzinger]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Marian]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Weber]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
</person-group>
<source><![CDATA[Purely URL based topic classification]]></source>
<year>2009</year>
<conf-name><![CDATA[ 18thInternational Conference on World Wide Web]]></conf-name>
<conf-date>2009</conf-date>
<conf-loc>Madrid, Spain </conf-loc>
</nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Uniform Resource Identifier (URI): Generic Syntax]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Berners-Lee]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Fielding]]></surname>
<given-names><![CDATA[R. T.]]></given-names>
</name>
<name>
<surname><![CDATA[Masinter]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
</person-group>
<source><![CDATA[Internet Society]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Boese]]></surname>
<given-names><![CDATA[E. S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Stereotyping the web: Genre Classification of Web Documents]]></source>
<year>2005</year>
<publisher-loc><![CDATA[USA ]]></publisher-loc>
<publisher-name><![CDATA[Colorado State University]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Boese]]></surname>
<given-names><![CDATA[E. S.]]></given-names>
</name>
<name>
<surname><![CDATA[Howe]]></surname>
<given-names><![CDATA[A. E.]]></given-names>
</name>
</person-group>
<source><![CDATA[Effects of web document evolution on genre classification]]></source>
<year>2005</year>
<conf-name><![CDATA[ CIKM'05]]></conf-name>
<conf-date>2005</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Craven]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[DiPasque]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Freitag]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[McCallum]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Mitchell]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Nigam]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Slattery]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Learning to extract symbolic knowledge from the World Wide Web]]></source>
<year>1998</year>
<conf-name><![CDATA[ 15thinnovative applications of artificial intelligence]]></conf-name>
<conf-date>1998</conf-date>
<conf-loc>Madison </conf-loc>
</nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Dewdney]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Vaness-Dikema]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Macmillan]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
</person-group>
<source><![CDATA[The form is the Substance: Classification of Genres in Text]]></source>
<year>2001</year>
<conf-name><![CDATA[ 39thAnnual Meeting of the Association for Computational Linguistics]]></conf-name>
<conf-date>2001</conf-date>
<conf-loc>Toulouse, France </conf-loc>
</nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Finn]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Kushmerick]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
</person-group>
<source><![CDATA[Learning to classify documents according to genre]]></source>
<year>2003</year>
<conf-name><![CDATA[ Workshop Doing it with Style: Computational Approaches to Style Analysis and Synthesis]]></conf-name>
<conf-date>2003</conf-date>
<conf-loc>Acapulco, Mexico </conf-loc>
</nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Jebari]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
</person-group>
<source><![CDATA[Une nouvelle approche de categorisation flexible et incrementale de pages web par genres]]></source>
<year>2008</year>
<publisher-loc><![CDATA[Tunisia ]]></publisher-loc>
<publisher-name><![CDATA[Tunis El Manar University]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Jebari]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Arif]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
</person-group>
<source><![CDATA[A Multi-label and Adapative Genre Classification of Web Pages]]></source>
<year>2012</year>
<conf-name><![CDATA[ ICMLA]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Joachims]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
</person-group>
<source><![CDATA[Text categorization with support vector machines: learning with many relevant features]]></source>
<year>1998</year>
<conf-name><![CDATA[ 10thEuropean Conference on Machine Learning]]></conf-name>
<conf-date>1998</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Learning to recognize webpage genres]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kanaris]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Stamatatos]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
</person-group>
<source><![CDATA[Information Processing and Management Journal]]></source>
<year></year>
<volume>45</volume>
<numero>5</numero>
<issue>5</issue>
<page-range>499-512</page-range></nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Karlgren]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA["Stylistic experiments in information retrieval]]></article-title>
<person-group person-group-type="editor">
<name>
<surname><![CDATA[Strzalkowski]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
</person-group>
<source><![CDATA[Natural Language Information Retrieval]]></source>
<year>1999</year>
<page-range>147-66</page-range></nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kennedy]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Shepherd]]></surname>
</name>
</person-group>
<source><![CDATA[Automatic Identification of Home Pages on the Web]]></source>
<year>2005</year>
<conf-name><![CDATA[ 38thInternational Conference on System Sciences]]></conf-name>
<conf-date>2005</conf-date>
<conf-loc>Hawaii </conf-loc>
</nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kessler]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Nunberg]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Schiitze]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<source><![CDATA[Automatic detection of text genre]]></source>
<year>1997</year>
<conf-name><![CDATA[ Proceedings of the 35thACL]]></conf-name>
<conf-loc> </conf-loc>
<page-range>32-8</page-range></nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kim]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Ross]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Examining Variations of Prominent Features in Genre Classification]]></source>
<year>2008</year>
<conf-name><![CDATA[ HICSS Conference]]></conf-name>
<conf-date>2008</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B16">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Multiple Sets of Features for Automatic Genre Classification of Web Documents]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lim]]></surname>
<given-names><![CDATA[C. S.]]></given-names>
</name>
<name>
<surname><![CDATA[Lee]]></surname>
<given-names><![CDATA[K. J]]></given-names>
</name>
<name>
<surname><![CDATA[Kim]]></surname>
<given-names><![CDATA[G. C.]]></given-names>
</name>
</person-group>
<source><![CDATA[Information Processing and Management]]></source>
<year>2005</year>
<volume>41</volume>
<numero>5</numero>
<issue>5</issue>
<page-range>1263-76</page-range></nlm-citation>
</ref>
<ref id="B17">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mason]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[An n-gram-based Approach to the Automatic Classification of Web Pages by Genre]]></source>
<year>2009</year>
<publisher-loc><![CDATA[Canada ]]></publisher-loc>
<publisher-name><![CDATA[Dalhousie University]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B18">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Meyer]]></surname>
<given-names><![CDATA[Z. E.]]></given-names>
</name>
</person-group>
<source><![CDATA[On Information Need and Categorizing Search]]></source>
<year>2007</year>
<publisher-loc><![CDATA[Germany ]]></publisher-loc>
<publisher-name><![CDATA[Paderborn University]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B19">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Meyer]]></surname>
<given-names><![CDATA[Z. E.]]></given-names>
</name>
<name>
<surname><![CDATA[Stein]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
</person-group>
<source><![CDATA[Genre classification of web pages: User study and feasibility analysis]]></source>
<year>2004</year>
<conf-name><![CDATA[ KI 2004: Advances in Artificial Intelligence]]></conf-name>
<conf-loc> </conf-loc>
<page-range>256-69</page-range></nlm-citation>
</ref>
<ref id="B20">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mitchell]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
</person-group>
<source><![CDATA[Machine learning]]></source>
<year>1997</year>
<publisher-name><![CDATA[McGraw-Hill]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B21">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Abramson]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Aha]]></surname>
<given-names><![CDATA[D. W.]]></given-names>
</name>
</person-group>
<source><![CDATA[What's in a URL? Genre Classification from URLs. Intelligent Techniques for Web Personalization and Recommender Systems]]></source>
<year>2012</year>
</nlm-citation>
</ref>
<ref id="B22">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Don't Use a Lot When Little Will Do: Genre Identification Using URLs]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Priyatam]]></surname>
<given-names><![CDATA[P. N.]]></given-names>
</name>
<name>
<surname><![CDATA[Iyengar]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Perumal]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Varma]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
</person-group>
<source><![CDATA[Research in Computing Science]]></source>
<year>2013</year>
<volume>70</volume>
<page-range>233-43</page-range></nlm-citation>
</ref>
<ref id="B23">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Santini]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[Automatic identification of genre in web pages]]></source>
<year>2007</year>
<publisher-loc><![CDATA[UK ]]></publisher-loc>
<publisher-name><![CDATA[Brighton University]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B24">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Stamatatos]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Fakotakis]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Kokkinakis]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
</person-group>
<source><![CDATA[Text Genre Detection Using Common Word Frequencies]]></source>
<year>2000</year>
<conf-name><![CDATA[ 18thInternational Conference on Computational Linguistics (COLING 2000)]]></conf-name>
<conf-date>2000</conf-date>
<conf-loc>Saarbrucken, Germany </conf-loc>
</nlm-citation>
</ref>
<ref id="B25">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Shepherd]]></surname>
<given-names><![CDATA[M. A.]]></given-names>
</name>
<name>
<surname><![CDATA[Watters]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
</person-group>
<source><![CDATA[Evolution of cybergenre]]></source>
<year>1998</year>
<conf-name><![CDATA[ 31ndHawaiian International Conference on System Sciences]]></conf-name>
<conf-date>1998</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B26">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Vapnik]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
</person-group>
<source><![CDATA[The Nature of Statistical Machine Learning Theory]]></source>
<year>1995</year>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B27">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Vidulin]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
<name>
<surname><![CDATA[Lustrek]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Gams]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[Using Genres to Improve Search Engines]]></source>
<year>2007</year>
<conf-name><![CDATA[ 1stInternational Workshop: Towards Genre-Enabled Search Engines: The Impact of Natural Language Processing]]></conf-name>
<conf-loc>Borovets, Bulgaria </conf-loc>
<page-range>45-51</page-range></nlm-citation>
</ref>
<ref id="B28">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Multi-Label Approaches to Web Genre Identification]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Vidulin]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
<name>
<surname><![CDATA[Lustrek]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Gams]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[Journal of Language and Computational Linguistics]]></source>
<year>2009</year>
<volume>24</volume>
<numero>1</numero>
<issue>1</issue>
<page-range>97-114</page-range></nlm-citation>
</ref>
<ref id="B29">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Witten]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Frank]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
</person-group>
<source><![CDATA[Data Mining: Practical Machine Learning Tools and Techniques]]></source>
<year>2005</year>
<publisher-loc><![CDATA[San Francisco ]]></publisher-loc>
<publisher-name><![CDATA[Morgan Kaufmann]]></publisher-name>
</nlm-citation>
</ref>
</ref-list>
</back>
</article>
