A Transformer-Based Approach to Authorship Attribution in Classical Arabic Texts
Source abstract
Abstract
Authorship attribution (AA) is a field of natural language processing that aims to attribute text to its author. Although the literature includes several studies on Arabic AA in general, applying AA to classical Arabic texts has not gained similar attention. This study focuses on investigating recent Arabic pretrained transformer-based models in a rarely studied domain with limited research contributions: the domain of Islamic law. We adopt an experimental approach to investigate AA. Because no dataset has been designed specifically for this task, we design and build our own dataset using Islamic law digital resources. We conduct several experiments on fine-tuning four Arabic pretrained transformer-based models: AraBERT, AraELECTRA, ARBERT, and MARBERT. Results of the experiments indicate that for the task of attributing a given text to its author, ARBERT and AraELECTRA outperform the other models with an accuracy of 96%. We conclude that pretrained transformer models, specifically ARBERT and AraELECTRA, fine-tuned using the Islamic legal dataset, show significant results in applying AA to Islamic legal texts.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Authorship Attribution and Profiling · Topic Modeling · Hate Speech and Cyberbullying Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Information Technology Department, College of Computer and Information Sciences, King Saud University, P.O. Box 145111, Riyadh 4545, Saudi Arabia
Funding
Research Center of the Female Scientific and Medical Colleges
References (58)
Show source-provided references
1. The Key Factors and Their Influence in Authorship Attribution10.13053/rcs-110-1-12 ↗
2. The Characteristic Curves of Composition10.1126/science.ns-9.214S.237 ↗
3. Zipf, G. (1932). Selected Studies of the Principle of Relative Frequency in Language, Harvard University Press.
4. On Sentence-Length as a Statistical Characteristic of Style in Prose: With Application to Two Cases of Disputed Authorship
5. Surveying Stylometry Techniques and Applications10.1145/3132039 ↗
6. Sayoud, H. (2014, January 10–14). Automatic authorship classification of two ancient books: Quran and Hadith. Proceedings of the 2014 IEEE/ACS 11th International Conference on Computer Systems and Applications (AICCSA), Doha, Qatar.10.1109/AICCSA.2014.7073263 ↗
7. A Survey on Authorship Attribution Issues of Arabic Text
8. Al-Sarem, M., Cherif, W., Wahab, A.A., Emara, A.H., and Kissi, M. (2018, January 24–25). Combination of stylo-based features and frequency-based features for identifying the author of short Arabic text. Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications, Rabat, Morocco.10.1145/3289402.3289500 ↗
9. Swain, S., Mishra, G., and Sindhu, C. (2017, January 20–22). Recent approaches on authorship attribution techniques—An overview. Proceedings of the 2017 International conference of Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India.10.1109/ICECA.2017.8203599 ↗
10. Stacked authorship attribution of digital texts10.1016/j.eswa.2021.114866 ↗
11. Authorship Attribution10.1561/1500000005 ↗
12. Using Relative Entropy for Authorship Attribution10.1007/11880592_8 ↗
13. Arabic Authorship Attribution Using Synthetic Minority Over-Sampling Technique and Principal Components Analysis for Imbalanced Documents10.4018/IJCINI.20211001.oa33 ↗
14. Naïve Bayes classifiers for authorship attribution of Arabic texts
15. Authorship Attribution of Arabic Articles
16. Rabab’ah, A., Al-Ayyoub, M., Jararweh, Y., and Aldwairi, M. (December, January 29). Authorship attribution of Arabic Tweets. Proceedings of the 2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA), Agadir, Morocco.10.1109/AICCSA.2016.7945818 ↗
17. Arabic Authorship Attribution10.1145/3236391 ↗
18. Abuhammad, Y. (2021, January 25–26). Authorship Attribution of Modern Standard Arabic Short Texts. Proceedings of the 2021 Arab Women in Computing Conference (ArabWIC’21), Sharjah, United Arab Emirates.10.1145/3485557.3485563 ↗
19. Towards Authorship Attribution in Arabic Short-Microblog Text10.1109/ACCESS.2021.3112624 ↗
20. A Comparative Survey of Authorship Attribution on Short Arabic Texts10.1007/978-3-319-99579-3_50 ↗
21. Bourib, S., and Sayoud, H. (2018, January 10–13). Author Identification on Noise Arabic Documents. Proceedings of the 2018 5th International Conference on Control, Decision and Information Technologies (CoDIT), Thessaloniki, Greece.10.1109/CoDIT.2018.8394885 ↗
22. Boukhaled, M.-A. (2022). Proceedings of the 14th International Conference on Agents and Artificial Intelligence, Vienna, Austria, 3–5 February 2022, SCITEPRESS–Science and Technology Publications.
23. Performance of authorship attribution classifiers with short texts: Application of religious Arabic fatwas
24. Ensemble Methods for Instance-Based Arabic Language Authorship Attribution10.1109/ACCESS.2020.2964952 ↗
25. Al-Yahya, M. (2018, January 18–24). Towards Automated Fiqh School Authorship Attribution. Proceedings of the 19th International Conference on Computational Linguistics and Intelligent Text Processing CICLing 2018, Hanoi, Vietnam.
26. Kalyan, K.S., Rajasekharan, A., and Sangeetha, S. (2021). AMMUS: A Survey of Transformer-based Pretrained Models in Natural Language Processing. arXiv.10.1016/j.jbi.2021.103982 ↗
27. Machine Learning and Deep Learning Methods for Cybersecurity10.1109/ACCESS.2018.2836950 ↗
28. Arabic Poetry Authorship Attribution using Machine Learning Techniques10.3844/jcssp.2019.1012.1021 ↗
29. Kalchbrenner, N., Grefenstette, E., and Blunsom, P. (2014). A Convolutional Neural Network for Modelling Sentences. arXiv.10.3115/v1/P14-1062 ↗
30. Liu, P., Qiu, X., and Huang, X. (2016). Recurrent Neural Network for Text Classification with Multi-Task Learning. arXiv.
31. Sutskever, I., Vinyals, O., and Le, Q.V. (2014). Sequence to Sequence Learning with Neural Networks. arXiv.
32. Deep neural network and model-based clustering technique for forensic electronic mail author attribution10.1007/s42452-020-04127-6 ↗
33. Modupe, A., Celik, T., Marivate, V., and Olugbara, O. (2022). Post-Authorship Attribution Using Regularized Deep Neural Network. Appl. Sci., 12.10.3390/app12157518 ↗
34. Bornon: Bengali Image Captioning with Transformer-Based Deep Learning Approach
35. Antoun, W., Baly, F., and Hajj, H. (2020). Araelectra: Pre-Training Text Discriminators for Arabic Language Understanding. arXiv.
36. Antoun, W., Baly, F., and Hajj, H. (2021). AraBERT: Transformer-based Model for Arabic Language Understanding. arXiv.
37. Abdul-Mageed, M., Elmadany, A., and Nagoudi, E.M.B. (2021). ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic. arXiv.10.18653/v1/2021.acl-long.551 ↗
38. The Effectiveness of Stemming in the Stylometric Authorship Attribution in Arabic
39. Fusion Based Authorship Attribution-Application of Comparison Between the Quran and Hadith
40. A Deep Learning-based Artificial Neural Network Method for Instance-based Arabic Language Authorship Attribution
41. Using Ontology for Revealing Authorship Attribution of Arabic Text10.35940/ijeat.C6412.049420 ↗
42. Authorship and Time Attribution of Arabic Texts Using JGAAP
43. Huertas-Tato, J., Huertas-Garcia, A., Martin, A., and Camacho, D. (2022). PART: Pre-trained Authorship Representation Transformer. arXiv.
44. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv.
45. Authorship Attribution for Social Media Forensics10.1109/TIFS.2016.2603960 ↗
46. Dipongkor, A.K., Islam, S., Kayesh, H., Hossain, S., Anwar, A., Rahman, K.A., and Razzak, I. (2021, January 18–21). DAAB: Deep Authorship Attribution in Bengali. Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China.10.1109/IJCNN52387.2021.9533619 ↗
47. Alrowili, S., and Shanker, V. (2021). Findings of the Association for Computational Linguistics: EMNLP 2021, Association for Computational Linguistics.
48. Wadhawan, A. (2021). Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT. arXiv.
49. Taboubi, B., Nessir, M.A.B., and Haddad, H. (2022, January 5–8). iCompass at CheckThat! 2022: ARBERT and AraBERT for Arabic Checkworthy Tweet Identification. Proceedings of the CLEF 2022: Conference and Labs of the Evaluation Forum, Bologna, Italy.
50. Towards Arabic aspect-based sentiment analysis: A transfer learning-based approach10.1007/s13278-021-00794-4 ↗
51. Fabien, M., Villatoro-Tello, E., Motlicek, P., and Parida, S. (2020, January 18–21). BertAA: BERT Fine-Tuning for Authorship Attribution. Proceedings of the 17th International Conference on Natural Language Processing, Patna, India.
52. Luyckx, K., and Daelemans, W. (, January 18–22). Authorship Attribution and Verification with Many Authors and Limited Data. Proceedings of the 22nd International Conference on Computational Linguistics—COLING ’08, Manchester, United Kingdom.
53. van Tussenbroek, T., Viering, T., Makrodimitris, S., Naseri, A., Tax, D., and Loog, M. (2020). Who said that? Comparing performance of TF-IDF and fastText to identify authorship of short sentences. [Bachelor’s Thesis, Delft University of Technology].
54. Prediction of geometry deviations in additive manufactured parts: Comparison of linear regression with machine learning algorithms10.1007/s10845-020-01567-0 ↗
55. Chadoulis, R.-T., Nikolaou, A., and Kotropoulos, C. (2022, January 7–9). Authorship Attribution in Greek Literature Using Word Adjacencies. Proceedings of the 12th Hellenic Conference on Artificial Intelligence, Corfu, Greece.10.1145/3549737.3549750 ↗
56. Das, K.A., Baruah, A., Barbhuiya, F.A., and Dey, K. (2020, January 22–25). Ensemble of ELECTRA for Profiling Fake News Spreaders. Proceedings of the CLEF 2020, Thessaloniki, Greece.
57. Mohaisen, D., and Jin, R. (2021). Computational Data and Social Networks, Springer. Lecture Notes in Computer Science.10.1007/978-3-030-91434-9 ↗
58. Romanov, A., Kurtukova, A., Shelupanov, A., Fedotova, A., and Goncharov, V. (2020). Authorship Identification of a Russian-Language Text Using Support Vector Machine and Deep Neural Networks. Futur. Internet, 13.10.3390/fi13010003 ↗