Elamur Research⌕
☰
home / papers / 2022 / A Survey of Plagiarism Detection Systems: Case of Use with English, French and Arabic Languages

A Survey of Plagiarism Detection Systems: Case of Use with English, French and Arabic Languages

Summary

The paper examines how well commercial and free plagiarism detection systems (PDS) support reviewers in English, French and Arabic academic settings. French and Arabic are rarely covered by such comparisons. The authors frame plagiarism detection as computer-assisted work: software surfaces textual similarity and links to sources, and a human decides whether it counts as plagiarism. They review earlier plagiarism typologies and propose their own, designed for comparing systems. They then build a purpose-made corpus and test eight systems on features, usability, technical aspects and detection quality. Detection is measured at three obfuscation levels: verbatim copying, paraphrase and cross-language (translated) reuse. They also probe "technical" exploits, tricks that alter the document rather than its wording yet can sharply lower detection scores. Overall, the tools have improved in functions, language coverage and source databases. Paraphrase detection is still weak, and translated plagiarism remains largely undetected. The work matters because institutions depend on these tools, and their blind spots are easy for plagiarists to exploit.

Key points

  • Eight systems were compared: Compilatio, Copyleaks, Docoloc, DupliChecker, Google Originality Reports, Oxsico, PlagiarismCheck.org and StrikePlagiarism.
  • Detection was tested on three obfuscation levels (verbatim, paraphrase, cross-language) across English, French and Arabic.
  • Workflow problems were common:
    • DupliChecker needed texts split into chunks under 1000 words and lacked batch processing.
    • Google OR accepted only the Google Docs format.
    • StrikePlagiarism's batch upload required a metadata spreadsheet plus a .zip archive.
  • In the usability ratings, DupliChecker scored lowest: ergonomics 2.25, online reports 1.5, offline reports 1.25.
  • A cited editor survey (Smart and Gaston, 2019) found that 24.8% of checked submissions exceeded 10% similarity.

Interesting ideas

  • I1. Detection is scored separately at graded difficulty tiers (exact copy, reworded, translated), which shows where a method breaks instead of hiding it in one average. — For Mova (learn): Build evaluation sets where the same content appears verbatim, paraphrased and restructured, and check that the extracted frames stay stable across tiers.
  • I2. The authors test tricks that change the file but not the visible wording, showing that systems can be fooled without any linguistic effort. — For Mova (tokens): Add a negative-control suite of such perturbed inputs to confirm the tokenizer and normalizer produce the same tokens and lemmas as for clean text.
  • I3. They recommend replacing a single overall similarity score with specific metrics and reports that show each matched passage next to its source. — For Mova (answer): Answers should come with the exact supporting spans and the frames they rely on, rather than a bare confidence number.
  • I4. Treating any text in parentheses as a valid citation causes both false positives and false negatives, so surface cues cannot stand in for real structure. — For Mova (tree): Identify citations and quotations through their syntactic attachment in the UD tree instead of punctuation heuristics, so attributed content is separated reliably.
  • I5. Cross-language reuse is the field's largest gap, because word-level matching cannot connect a text to its translation. — For Mova (back): Comparing meaning graphs from the meta-world, rather than strings, could flag that two texts in different languages express the same events and roles.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2201.03423 · arXiv 2201.03423

@misc{abdelhamid2022survey,
  title = {{A Survey of Plagiarism Detection Systems: Case of Use with English, French and Arabic Languages}},
  author = {Abdelhamid, Mehdi and Azouaou, Faical and Batata, Sofiane},
  year = {2022},
  doi = {10.48550/arxiv.2201.03423},
  eprint = {2201.03423},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2201.03423}
}

References

28 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ali, A., Abdulla, H., & Snášel, V. (2011). Overview and Comparison of Plagiarism Detection Tools. VSB-Technical University of Ostrava. find
  2. Birkić, T., Celjak, D., Cundeković, M., & Rako, S. (2016). Analysis of software for plagiarism detection in science and education. Report. University of Zagreb, 26p. find
  3. Chow, Y., Susilo, W., Pranata, I., Barmawi, A., 2016. Detecting visual spoofing using classical cryptanalysis methods in plagiarism detection systems. undefined. find
  4. Chowdhury, H.A., Bhattacharyya, D.K., 2018. Plagiarism: Taxonomy, Tools and Detection Techniques. arXiv. https://arxiv.org/abs/1801.06323 ↗
  5. Comas-Forgas, R., & Sureda-Negre, J. (2010). Academic Plagiarism: Explanatory Factors from Students’ Perspective. Journal of Academic Ethics, 8(3), 217–232. https://doi.org/10.1007/s10805-010-9121-0 ↗
  6. Eassom, H. (2016, February 2). 10 types of plagiarism in research. https://www.wiley.com/network/researchers/submission-and-navigating-peer-review/10-types-of-plagiarism-in-research ↗
  7. Evans Connor. (2020). Six Proven ways to cheat Turnitin - Paper Per Hour. https://paperperhour.com/six-proven-ways-cheat-turnitin/ ↗
  8. Fishman, T. (2009). “We know it when we see it” is not good enough: toward a standard definition of plagiarism that transcends theft, fraud, and copyright. 4th Asia Pacific Conference on Educational Integrity (4APCEI). https://ro.uow.edu.au/apcei/09/papers/37 ↗
  9. Foltýnek, T., Dlabolová, D., Anohina-Naumeca, A., Razı, S., Kravjar, J., Kamzola, L., Guerrero-Dib, J., Çelik, Ö., & Weber-Wulff, D. (2020). Testing of support tools for plagiarism detection. International Journal of Educational Technology in Higher Education, 17(1), 46. https://doi.org/10.1186/s41239-020-00192-4 ↗
  10. Foltýnek, T., Meuschke, N., & Gipp, B. (2019). Academic plagiarism detection: A systematic literature review. In ACM Computing Surveys (Vol. 52, Issue 6). Association for Computing Machinery. https://doi.org/10.1145/3345317 ↗
  11. International Organization for Standardization [ISO]. (2001, June). ISO/IEC 9126-1:2001 Software engineering — Product quality. http://www.arisa.se/compendium/node6.html ↗
  12. Jharotia, A.-K., 2018. Plagiarism Detection Through Software in Digital World. JK Business School, Gurugram, Haryana. find
  13. Khan, N., Agrawal, C., Nishat Ansari, T., 2018. A Review on Various Plagiarism Detection Systems Based on Exterior and Interior Method. IJARCCE 7, 6–12. https://doi.org/10.17148/ijarcce.2018.792 ↗
  14. Kumar, S., Boriwal, C., 2019. Plagiarism Issues: Types, Tools and Remedies, Indian Journal of Agricultural Library and Information Services. find
  15. Lim, S. (2009). How and why do college students use Wikipedia? Journal of the American Society for Information Science and Technology, 60(11), 2189–2202. https://doi.org/10.1002/asi.21142 ↗
  16. Maurer, H., Kappe, F., & Zaka, B. (2006). Plagiarism - A Survey. Journal of Universal Computer Science, 12, 1050–1084. find
  17. Mozgovoy, M., Kakkonen, T., & Cosma, G. (2010). Automatic student plagiarism detection: Future perspectives. Journal of Educational Computing Research, 43(4), 511–531. https://doi.org/10.2190/EC.43.4.e ↗
  18. Nahas, M. N. (2017). Survey and Comparison between Plagiarism Detection Tools. Mahmoud Nadim Nahas. Survey and Comparison between Plagiarism Detection Tools. American Journal of Data Mining and Knowledge Discovery, 2(2), 50–53. https://doi.org/10.11648/j.ajdmkd.20170202.12 ↗
  19. Park, C. (2003). In other (People’s) words: Plagiarism by university students-literature and lessons. In Assessment and Evaluation in Higher Education (Vol. 28, Issue 5, pp. 471–488). Taylor & Francis Group . https://doi.org/10.1080/02602930301677 ↗
  20. Selemani, A., Chawinga, W. D., & Dube, G. (2018). Why do postgraduate students commit plagiarism? An empirical study. International Journal for Educational Integrity, 14(1), 7. https://doi.org/10.1007/s40979-018-0029-6 ↗
  21. Shkodkina, Y., & Pakauskas, D. (2017). Comparative Analysis of Plagiarism Detection Systems. Business Ethics and Leadership, 1(3), 27–35. https://doi.org/10.21272/bel.1(3).27-35.2017 ↗
  22. Smart, P., Gaston, T., 2019. How prevalent are plagiarized submissions? Global survey of editors. Learned Publishing 32, 47–56. https://doi.org/10.1002/leap.1218 ↗
  23. Sobhagyawati, G., 2017. Plagiarism Detection Software: an Overview, in: Emerging Trends and Technology in Knowledge Management. Prateeksha Publications, Jaipur, pp. 129–143. find
  24. Turnitin. (2012). The Plagiarism Spectrum (white paper). https://www.turnitin.com/resources/plagiarism-spectrum-2-0 ↗
  25. Vani, K., Gupta, D., 2016. Study on extrinsic text plagiarism detection techniques and tools. Journal of Engineering Science and Technology Review 9, 150–164. https://doi.org/10.25103/jestr.094.23 ↗
  26. Velásquez, J. D., Covacevich, Y., Molina, F., Marrese-Taylor, E., Rodríguez, C., & Bravo-Marquez, F. (2016). DOCODE 3.0 (DOcument COpy DEtector): A system for plagiarism detection by applying an information fusion process from multiple documental data sources. Information Fusion, 27, 64–75. https://doi.org/10.1016/j.inffus.2015.05.006 ↗
  27. Weber-Wulff, D. (2014). Plagiarism and Academic Misconduct. In False Feathers (pp. 3–27). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-39961-9_2 ↗
  28. Weber-Wulff, D. (2015). Plagiarism Detection Software: Promises, Pitfalls, and Practices. In Handbook of Academic Integrity (pp. 1–10). Springer Singapore. https://doi.org/10.1007/978-981-287-079-7_19-1 ↗

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/abdelhamid-2022-survey-plagiarism-detection-systems-case/