@inproceedings{Meuschke2017Analy-41875,
  year={2017},
  doi={10.1145/3132847.3133144},
  title={Analyzing Mathematical Content to Detect Academic Plagiarism},
  isbn={978-1-4503-4918-5},
  publisher={ACM Press},
  address={New York, New York, USA},
  booktitle={CIKM 2017 : proceedings of the 2017 ACM Conference on Information and Knowledge Management : November 6-10, 2017, Singapore},
  pages={2211--2214},
  editor={Lim, Ee-Peng},
  author={Meuschke, Norman and Schubotz, Moritz and Hamborg, Felix and Skopal, Tomas and Gipp, Bela}
}

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/41875">
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/41875/1/Meuschke_2-wy9aqw7lbcn20.pdf"/>
    <dc:creator>Hamborg, Felix</dc:creator>
    <dc:contributor>Gipp, Bela</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-03-21T11:01:42Z</dc:date>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/41875/1/Meuschke_2-wy9aqw7lbcn20.pdf"/>
    <dc:language>eng</dc:language>
    <dc:contributor>Hamborg, Felix</dc:contributor>
    <dcterms:abstract xml:lang="eng">This paper presents, to our knowledge, the first study on analyzing mathematical expressions to detect academic plagiarism. We make the following contributions. First, we investigate confirmed cases of plagiarism to categorize the similarities of mathematical content commonly found in plagiarized publications. From this investigation, we derive possible feature selection and feature comparison strategies for developing math-based detection approaches and a ground truth for our experiments. Second, we create a test collection by embedding confirmed cases of plagiarism into the NTCIR-11 MathIR Task dataset, which contains approx. 60 million mathematical expressions in 105,120 documents from arXiv.org. Third, we develop a first math-based detection approach by implementing and evaluating different feature comparison approaches using an open source parallel data processing pipeline built using the Apache Flink framework. The best performing approach identifies all but two of our real-world test cases at the top rank and achieves a mean reciprocal rank of 0.86. The results show that mathematical expressions are promising text-independent features to identify academic plagiarism in large collections. To facilitate future research on math-based plagiarism detection, we make our source code and data available.</dcterms:abstract>
    <dc:creator>Meuschke, Norman</dc:creator>
    <dc:creator>Gipp, Bela</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:creator>Skopal, Tomas</dc:creator>
    <dcterms:issued>2017</dcterms:issued>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/41875"/>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:title>Analyzing Mathematical Content to Detect Academic Plagiarism</dcterms:title>
    <dc:contributor>Skopal, Tomas</dc:contributor>
    <dc:contributor>Schubotz, Moritz</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Meuschke, Norman</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Schubotz, Moritz</dc:creator>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-03-21T11:01:42Z</dcterms:available>
  </rdf:Description>
</rdf:RDF>