Navigationsweiche Anfang

Navigationsweiche Ende


Resources Doctoral Thesis

Below you find the source code, data, and other resources for my doctoral thesis

Analyzing Non-Textual Content Elements to Detect Academic Plagiarism 

 


 

Hybrid Plagiarism Detection Systems HyPlag

Demo system 
  (user: guest@hyplag.org | pw: hybridPD)

  Source code 
  (login to GitHub first! user: hyplag-guest | pw: hybridPD20)
        Backend
        Frontend

 


 

Citation-based Plagiarism Detection

  Source Code: see HyPlag source code above

  Reference collection: 185,170 documents from PMC OAS collection, included in the CITREC dataset
        Database (5 GB zipped, ~20 GB raw) — includes document metadata, citation data and pre-computed similarity scores

User-perceived cases of plagiarism
  (available upon request)

 


 

Image-based Plagiarism Detection

Source Code

Data:15 test cases, 10,000 images from PMC OAS as reference collection
  (547 MB zipped) 

 


 

Mathematics-based Plagiarism Detection

  Source Code: see HyPlag source code above

Test cases: 10 confirmed cases of plagiarism available as PDF and TEI
  (login to GitHub first! user: hyplag-guest | pw: hybridPD20)

Reference collection: 105,120 arXiv documents converted to XHMTL

 

zuletzt bearbeitet am: 20.05.2021