Thesis Open Access

Analyzing Non-Textual Content Elements to Detect Academic Plagiarism

Meuschke, Norman


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.4913345</identifier>
  <creators>
    <creator>
      <creatorName>Meuschke, Norman</creatorName>
      <givenName>Norman</givenName>
      <familyName>Meuschke</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-4648-8198</nameIdentifier>
      <affiliation>University of Konstanz</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Analyzing Non-Textual Content Elements to Detect Academic Plagiarism</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2021</publicationYear>
  <subjects>
    <subject>Plagiarism Detection</subject>
    <subject>Plagiarism Detection Technology</subject>
    <subject>Citation Analysis</subject>
    <subject>Content-based Image Retrieval</subject>
    <subject>Math Retrieval</subject>
    <subject>Natural Language Processing</subject>
    <subject>Information Visualization</subject>
    <subject>User Interaction</subject>
    <subject>Open Source Software</subject>
  </subjects>
  <contributors>
    <contributor contributorType="Supervisor">
      <contributorName>Gipp, Bela</contributorName>
      <givenName>Bela</givenName>
      <familyName>Gipp</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-6522-3019</nameIdentifier>
      <affiliation>University of Konstanz</affiliation>
    </contributor>
    <contributor contributorType="Supervisor">
      <contributorName>Reiterer, Harald</contributorName>
      <givenName>Harald</givenName>
      <familyName>Reiterer</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-8528-8928</nameIdentifier>
      <affiliation>University of Konstanz</affiliation>
    </contributor>
    <contributor contributorType="Supervisor">
      <contributorName>Nelson, Michael L.</contributorName>
      <givenName>Michael L.</givenName>
      <familyName>Nelson</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-3749-8116</nameIdentifier>
      <affiliation>Old Dominion University</affiliation>
    </contributor>
  </contributors>
  <dates>
    <date dateType="Issued">2021-06-10</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Text">Thesis</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/4913345</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.4913344</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Identifying academic plagiarism is a pressing problem, among others, for research institutions, publishers, and funding organizations. Detection approaches proposed so far analyze lexical, syntactical, and semantic text similarity. These approaches find copied, moderately reworded, and literally translated text. However, reliably detecting disguised plagiarism, such as strong paraphrases, sense-for-sense translations, and the reuse of non-textual content and ideas, is an open research problem.&lt;br&gt;
The thesis addresses this problem by proposing plagiarism detection approaches that implement a different concept: analyzing non-textual content in academic documents, specifically citations, images, and mathematical content.&lt;br&gt;
To validate the effectiveness of the proposed detection approaches, the thesis presents five evaluations that use real cases of academic plagiarism and exploratory searches for unknown cases.&lt;br&gt;
The evaluation results show that non-textual content elements contain a high degree of semantic information, are language-independent, and largely immutable to the alterations that authors typically perform to conceal plagiarism. Analyzing non-textual content complements text-based detection approaches and increases the detection effectiveness, particularly for disguised forms of academic plagiarism.&lt;br&gt;
To demonstrate the benefit of combining non-textual and text-based detection methods, the thesis describes the first plagiarism detection system that integrates the analysis of citation-based, image-based, math-based, and text-based document similarity. The system&amp;#39;s user interface employs visualizations that significantly reduce the effort and time users must invest in examining content similarity.&lt;/p&gt;</description>
    <description descriptionType="Other">Doctoral Thesis</description>
  </descriptions>
</resource>
95
58
views
downloads
All versions This version
Views 9595
Downloads 5858
Data volume 619.1 MB619.1 MB
Unique views 6969
Unique downloads 4444

Share

Cite as