<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>2838</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>IV,50,xiv</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>masterthesis</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>2022-05-20</thesisDateAccepted>
    <title language="eng">Website Taxonomy Extraction – Identifying and Extracting Navigation Structures from Websites</title>
    <abstract language="eng">Publishers of websites want their information to be as accessible as possible to visitors. How­ever, the navigation menus on websites nowadays have become quite complex and limit this accessibility of information. In order to pave a way for browser extensions that are able to transform the rigid navigation in terms of both the layout and the structure, the taxonomy embedded in the HTML-navigation must be extracted first. &#13;
This thesis will show that it is possible to identify the root node of a multi layer website navigation in O( [links in the DOM tree] * [height of the DOM tree] ) time and extract the embedded taxonomy in O( [links in the navigation tree] * [height of the navigation tree] ) time, while analyzing only the startpage of a website. &#13;
In order to obtain a complete overview of the website, the algorithm goes on by merging all links of subsequent webpages into the context of the taxonomy extracted from the startpage. &#13;
By keeping the hierarchical information intact it enables a completely new approach to develop­ing applications for improving accessibility and usability of website navigation: The navigation structure can now be reproduced and enhanced in terms of markup, layout and functionality. &#13;
lt also opens context based semantics of navigation taxonomies as a new research field, which will yield new solutions for better understandable information architectures.</abstract>
    <identifier type="doi">10.60524/opus-2838</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="frontdoor_url">https://opus4.kobv.de/opus4-hs-augsburg/2838</enrichment>
    <enrichment key="OpenAccess">ja</enrichment>
    <licence>Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International</licence>
    <author>Ralph Voigt</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Barrierefreiheit</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Website-Navigation</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Taxonomie</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Taxonomie-Mining</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>accessibility</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>website navigation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>taxonomy</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>taxonomy mining</value>
    </subject>
    <collection role="ddc" number="004">Datenverarbeitung; Informatik</collection>
    <collection role="open_access" number="">open_access</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <collection role="DFG-Fachsystematik" number="409">Informatik</collection>
    <file>https://opus4.kobv.de/opus4-hs-augsburg/files/2838/MA_Voigt_Ralph.pdf</file>
  </doc>
</export-example>
