EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Plagiarism detection across languages: a comprehensive study of Arabic and English-to-Arabic long documents

Ahmad Abdelaal, Abdallah Elsaadany, Abdelrhman Ahmed Medhat, Aysha Al Shamsi, Noha Gamal ElDin Saad Ali

PeerJ Computer Science · 25.08.2025 · 11 · e3128

DOI: 10.7717/peerj-cs.3128 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 25.08.2025. Verfasst von Ahmad Abdelaal und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Technology and Computer Science, Nile University, Giza, Egypt. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Plagiarism detection in Arabic texts remains a significant challenge due to the complex morphological structure, rich linguistic diversity, and scarcity of high-quality labeled datasets. This study proposes a robust framework for Arabic plagiarism detection by integrating Siamese neural networks (SNN) with state-of-the-art transformer architectures, specifically AraT5 and Longformer. The system employs a hybrid workflow, combining transformer-based encoders and a classification objective to implicitly learn textual similarity. To address the inherent imbalance in Arabic plagiarism datasets, both weighted cross-entropy loss and Dice loss functions were utilized to optimize model training. Extensive experiments were conducted using the ExAraCorpusPAN2015 dataset, demonstrating the effectiveness of the proposed architecture. Results indicate that AraT5 with weighted cross-entropy loss outperformed other configurations, achieving an F1-score of 0.9058. Additionally, comparative analysis with existing methodologies highlights the superiority of our approach in handling nuanced semantic and structural variations within Arabic texts. This study underscores the importance of transformer-based architectures and class-specific loss functions in enhancing plagiarism detection accuracy in under-resourced languages like Arabic.

Schlagwörter

Stichwörter der Autor:innen

AraT5Arabic plagiarism detectionLongformerSiamese neural network

Autor:innen und Institutionen

  • School of Information Technology and Computer Science, Nile University, Giza, Egypt.
  • Arabic Language Section, Mohamed Bin Zayed University for Humanities, Abu Dhabi, United Arab Emirates.

Zitieren

APA

Abdelaal, A., Elsaadany, A., Medhat, A. A., Al Shamsi, A., & ElDin Saad Ali, N. G. (2025). Plagiarism detection across languages: a comprehensive study of Arabic and English-to-Arabic long documents. PeerJ Computer Science, 11, e3128. https://doi.org/10.7717/peerj-cs.3128

Vancouver

Abdelaal A, Elsaadany A, Medhat AA, Al Shamsi A, ElDin Saad Ali NG. Plagiarism detection across languages: a comprehensive study of Arabic and English-to-Arabic long documents. PeerJ Computer Science. 2025;11:e3128. doi:10.7717/peerj-cs.3128

BibTeX
@article{Abdelaal2025,
  author = {Abdelaal, Ahmad and Elsaadany, Abdallah and Medhat, Abdelrhman Ahmed and Al Shamsi, Aysha and ElDin Saad Ali, Noha Gamal},
  title = {Plagiarism detection across languages: a comprehensive study of Arabic and English-to-Arabic long documents},
  journal = {PeerJ Computer Science},
  year = {2025},
  volume = {11},
  pages = {e3128},
  doi = {10.7717/peerj-cs.3128}
}
Kostenlos starten →