{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T14:02:05Z","timestamp":1773842525694,"version":"3.50.1"},"reference-count":55,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"content-version":"vor","delay-in-days":307,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,1,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Cyberbullying is a significant issue on social media platforms. It poses serious emotional consequences and harassment to victims. Conventional pre-trained language models, such as Bidirectional Encoder Representations from Transformers (BERT), have achieved significant success in detecting cyberbullying through the analysis of natural language texts, especially with resource-rich languages such as English. However, for low-resource languages, such as Arabic, there has been limited attention given to the detection of cyberbullying. This research investigates the effectiveness of Arabic BERT (AraBERT), a pre-trained language model, for detecting Arabic cyberbullying comments. It also explores the trade-off between computational resources and model performance through various fine-tuning and freezing strategies. From an initial pool of &amp;gt;40\u2009000 collected comments, we constructed a high-quality, balanced dataset of 20\u2009000 Facebook comments written in Arabic. This subset was then manually labeled as either bullying or non-bullying to ensure data reliability and to facilitate robust model training. We employed fine-tuning techniques to adapt AraBERTv2 to the cyberbullying detection task. Through experimentation with layer freezing technique, we explored the trade-off between leveraging pre-trained knowledge and adapting the model to the specific task. Our findings demonstrate that fine-tuning all layers of AraBERTv2, which involves adjusting the weights and biases of each layer during training, achieved the highest performance. This approach offers a flexible method for applying a pre-trained model to new problems, resulting in an accuracy of 91.9% and an F1 score of 92.8%.<\/jats:p>","DOI":"10.1093\/cybsec\/tyaf030","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T12:13:35Z","timestamp":1759925615000},"source":"Crossref","is-referenced-by-count":1,"title":["AraBERT for Arabic cyberbullying detection in Facebook comments"],"prefix":"10.1093","volume":"11","author":[{"given":"Rania Ibrahim","family":"Hithnawi","sequence":"first","affiliation":[{"name":"Arab American University Department of Engineering and Technology Sciences, , Zababdeh, 042, Jenin, P.O. Box 240 ,","place":["Palestine"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8545-1254","authenticated-orcid":false,"given":"Mohammad M N","family":"Hamarsheh","sequence":"additional","affiliation":[{"name":"Arab American University Department of Computer Science and Networks Security, , Zababdeh, 042, Jenin, P.O. Box 240 ,","place":["Palestine"]}]},{"given":"Mohammed","family":"Maree","sequence":"additional","affiliation":[{"name":"Arab American University Department of Information Technology, , Zababdeh, 042, Jenin, P.O. Box 240 ,","place":["Palestine"]}]}],"member":"286","published-online":{"date-parts":[[2025,11,4]]},"reference":[{"key":"2025110419273164800_bib1","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1093\/cybsec\/tyae026","article-title":"Cyberbullying on social media: definitions, prevalence, and impact challenges","volume":"10","author":"Ray","year":"2024","journal-title":"J Cybersecur"},{"key":"2025110419273164800_bib2","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1192\/pb.bp.112.040840","article-title":"Cyberbullying and its impact on young people\u2019s emotional health and well-being","volume":"37","author":"Cowie","year":"2013","journal-title":"Psychiatrist"},{"key":"2025110419273164800_bib3","doi-asserted-by":"publisher","first-page":"187","DOI":"10.3390\/fi12110187","article-title":"A comparative analysis of machine learning techniques for cyberbullying detection on Twitter","volume":"12","author":"Muneer","year":"2020","journal-title":"Future Internet"},{"key":"2025110419273164800_bib4","doi-asserted-by":"publisher","first-page":"634909","DOI":"10.3389\/fpubh.2021.634909","article-title":"Cyberbullying among adolescents and children: a comprehensive review of the global situation, risk factors, and preventive measures","volume":"9","author":"Zhu","year":"2021","journal-title":"Front Public Health"},{"key":"2025110419273164800_bib5","doi-asserted-by":"publisher","first-page":"e202344","DOI":"10.30935\/ojcmt\/13478","article-title":"Effect of online civic intervention and online disinhibition on online hate speech among digital media users","volume":"13","author":"Aljasir","year":"2023","journal-title":"Online J Commun Media Technol"},{"key":"2025110419273164800_bib6","doi-asserted-by":"publisher","first-page":"3057","DOI":"10.17507\/tpls.1410.06","article-title":"The role of culture in abusive language on social media: examining the use of english and arabic derogatory terms","volume":"14","author":"Alshalabi","year":"2024","journal-title":"tpls"},{"key":"2025110419273164800_bib7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42979-022-01308-5","article-title":"An application to detect cyberbullying using machine learning and deep learning techniques","volume":"3","author":"Raj","year":"2022","journal-title":"Sn Comput Sci."},{"key":"2025110419273164800_bib8","doi-asserted-by":"crossref","first-page":"3567","DOI":"10.3390\/math11163567","article-title":"Cyberbullying detection on Twitter using deep learning-based attention mechanisms and continuous bag of words feature extraction","volume":"11","author":"Muneer","year":"2023","journal-title":"Mathematics"},{"key":"2025110419273164800_bib9","doi-asserted-by":"publisher","first-page":"1375","DOI":"10.1007\/s10462-023-10553-w","article-title":"Cyberbullying detection and machine learning: a systematic literature review","volume":"56","author":"Balakrisnan","year":"2023","journal-title":"Artif Intell Rev"},{"key":"2025110419273164800_bib10","doi-asserted-by":"publisher","first-page":"179","DOI":"10.3390\/fi15050179","article-title":"A review on deep-learning-based cyberbullying detection","volume":"15","author":"Hasan","year":"2023","journal-title":"Future Internet"},{"key":"2025110419273164800_bib11","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.34028\/iajit\/21\/6\/9","article-title":"Cyberbullying detection in social networks using deep learning","volume":"21","author":"Khafajeh","year":"2024","journal-title":"IAJIT"},{"key":"2025110419273164800_bib12","doi-asserted-by":"publisher","first-page":"1839","DOI":"10.1007\/s00530-020-00701-5","article-title":"Cyberbullying detection solutions based on deep learning architectures","volume":"29","author":"Iwendi","year":"2023","journal-title":"Multimedia Syst"},{"key":"2025110419273164800_bib13","doi-asserted-by":"publisher","first-page":"103454","DOI":"10.1016\/j.ipm.2023.103454","article-title":"Cyberbullying detection for low-resource languages and dialects: review of the state of the art","volume":"60","author":"Mahmud","year":"2023","journal-title":"Inform Process Manage"},{"key":"2025110419273164800_bib14","volume-title":"Ethnologue: Languages of the World","author":"SIL International","year":"2022","edition":"25th ed."},{"key":"2025110419273164800_bib15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1142\/10693","article-title":"Challenges in arabic natural language processing","author":"Shaalan","year":"2018","journal-title":"Comput Linguist Speech Image Process Arabic Lang"},{"key":"2025110419273164800_bib16","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1007\/978-3-031-64650-8_42","article-title":"Arabic named Entity recognition: approaches, datasets, and comparative study","volume":"1048","author":"El\u00a0Gougi","year":"2024","journal-title":"Lecture Notes Netw Syst"},{"key":"2025110419273164800_bib17","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/s10772-015-9290-8","article-title":"A frame-based approach for capturing semantics from Arabic text for text-to-sign language MT","volume":"19","author":"Lakhfif","year":"2016","journal-title":"Int J Speech Technol"},{"key":"2025110419273164800_bib18","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/v1\/N19-1423","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North.","author":"Devlin","year":"2019"},{"key":"2025110419273164800_bib19","first-page":"4143","article-title":"Visualizing and understanding the effectiveness of BERT","volume-title":"EMNLP-IJCNLP 2019\u20132019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference","author":"Hao","year":"2019"},{"key":"2025110419273164800_bib20","first-page":"345","article-title":"SarcasmDet at Sarcasm Detection Task 2021 in Arabic using AraBERT pretrained model","author":"Faraj","year":"2021"},{"key":"2025110419273164800_bib21","article-title":"AraBERT: transformer-based model for arabic language understanding","author":"Antoun","year":"2020"},{"key":"2025110419273164800_bib22","doi-asserted-by":"publisher","first-page":"41","DOI":"10.5815\/ijitcs.2021.05.04","article-title":"Data mining for cyberbullying and harassment detection in arabic texts","volume":"13","author":"Bashir","year":"2021","journal-title":"IJITCS"},{"key":"2025110419273164800_bib23","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA47632.2019.9035276","article-title":"Detection of Arabic cyberbullying on Social networks using machine Learning","volume-title":"ACS\/IEEE International Conference on Computer Systems and Applications","author":"Mouheb","year":"2019"},{"key":"2025110419273164800_bib24","doi-asserted-by":"publisher","DOI":"10.1109\/ICONSCEPT61884.2024.10627823","article-title":"Enhancing cyberbullying detection through keyword filtering: a comparative study of ML and DL approaches","volume-title":"2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024\u2013Proceedings","author":"Kaarthika","year":"2024"},{"key":"2025110419273164800_bib25","first-page":"2330","article-title":"Automatic cyber bullying detection in arabic social media","volume":"12","author":"AlHarbi","year":"2019","journal-title":"Int J Engineer Res Technol"},{"key":"2025110419273164800_bib26","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.procs.2018.10.473","article-title":"Dataset construction for the detection of anti-social behaviour in online communication in Arabic","volume":"142","author":"Alakrot","year":"2018","journal-title":"Procedia Comput Sci"},{"key":"2025110419273164800_bib27","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.procs.2018.10.491","article-title":"Towards accurate detection of offensive language in online communication in Arabic","volume":"142","author":"Alakrot","year":"2018","journal-title":"Procedia Comput Sci"},{"key":"2025110419273164800_bib28","first-page":"3273","article-title":"Cyberbullying identification system based deep learning algorithms","volume":"11","author":"Aldhyani","year":"2022","journal-title":"Electronics (Basel)"},{"key":"2025110419273164800_bib29","doi-asserted-by":"publisher","first-page":"101652","DOI":"10.1016\/j.jksuci.2023.101652","article-title":"Cyberbullying detection framework for short and imbalanced arabic datasets","volume":"35","author":"Alzaqebah","year":"2023","journal-title":"J King Saud Univ Comput Inform Sci"},{"key":"2025110419273164800_bib30","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.32604\/cmc.2020.09962","article-title":"MII: a novel text classification model combining deep active learning with BERT","volume":"63","author":"Zhang","year":"2020","journal-title":"Comput Mater Continua"},{"key":"2025110419273164800_bib31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13278-023-01158-w","article-title":"Enhancing cyberbullying detection: a comparative study of ensemble CNN\u2013SVM and BERT models","volume":"14","author":"Saini","year":"2024","journal-title":"Soc Netw Anal Min"},{"key":"2025110419273164800_bib32","doi-asserted-by":"publisher","first-page":"147","DOI":"10.3390\/brainsci13010147","article-title":"Using the AraBERT model for customer satisfaction classification of telecom sectors in Saudi Arabia","volume":"13","author":"Aftan","year":"2023","journal-title":"Brain Sci"},{"key":"2025110419273164800_bib33","doi-asserted-by":"publisher","first-page":"379","DOI":"10.11591\/ijai.v11.i1.pp379-387","article-title":"AraBERT transformer model for Arabic comments and reviews analysis","volume":"11","author":"EL\u00a0Moubtahij","year":"2022","journal-title":"IJ-AI"},{"key":"2025110419273164800_bib34","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1109\/ICCICC57084.2022.10101577","article-title":"Arabic hate speech detection system based on AraBERT","volume-title":"2022 IEEE 21st International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","author":"Salomon","year":"2022"},{"key":"2025110419273164800_bib35","unstructured":"Nada AMA, Alajrami E, Alsaqqa A \u00a0et al. \u00a0Arabic text summarization using AraBERT model using extractive text summarization approach. International Journal of Academic Information Systems Research (IJAISR). 2020, 10 August 2020. 10.5281\/zenodo.3978186"},{"key":"2025110419273164800_bib36","first-page":"208","article-title":"Arabic hate speech detection system based on AraBERT","volume-title":"IEEE 21st International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","author":"Salomon","year":"2022"},{"key":"2025110419273164800_bib37","doi-asserted-by":"publisher","first-page":"6048","DOI":"10.1016\/j.jksuci.2021.07.013","article-title":"A multilingual offensive language detection method based on transfer learning from transformer fine-tuning model","volume":"34","author":"El-Alami","year":"2022","journal-title":"J King Saud Univ Comput Inform Sci"},{"key":"2025110419273164800_bib38","first-page":"395","article-title":"AraBERT and Farasa segmentation based approach for sarcasm and sentiment detection in arabic tweets","volume-title":"WANLP 2021\u20136th Arabic Natural Language Processing Workshop, Proceedings of the Workshop.","author":"Wadhawan","year":"2021"},{"key":"2025110419273164800_bib39","first-page":"323","article-title":"ArSarcasm shared task: an ensemble BERT model for SarcasmDetection in arabic tweets","author":"Bashmal","year":"2021"},{"key":"2025110419273164800_bib40","doi-asserted-by":"publisher","first-page":"69","DOI":"10.3390\/informatics8040069","article-title":"Arabic offensive and hate speech detection using a cross-corpora multi-task learning model","volume":"8","author":"Aldjanabi","year":"2021","journal-title":"Informatics"},{"key":"2025110419273164800_bib41","doi-asserted-by":"publisher","first-page":"5720","DOI":"10.3390\/app12115720","article-title":"BERT models for Arabic text classification: a systematic review","volume":"12","author":"Alammary","year":"2022","journal-title":"Appl Sci"},{"key":"2025110419273164800_bib42","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1017\/S135132492100019X","article-title":"Creation of annotated country-level dialectal Arabic resources: an unsupervised approach","volume":"28","author":"Althobaiti","year":"2022","journal-title":"Nat Lang Eng"},{"key":"2025110419273164800_bib43","article-title":"Automatic Arabic dialect identification Systems for written texts: a survey","author":"Althobaiti","year":"2020"},{"key":"2025110419273164800_bib44","article-title":"Apify","author":"APIFY","year":"2024"},{"key":"2025110419273164800_bib45","article-title":"A beginner\u2019s guide to tokens, vectors, and embeddings in NLP","author":"Metzger","year":"2020"},{"key":"2025110419273164800_bib46","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1162\/tacl_a_00349","article-title":"A primer in BERTology: what we know about how BERT works","volume":"8","author":"Rogers","year":"2020","journal-title":"Trans Assoc Comput Linguist"},{"key":"2025110419273164800_bib47","doi-asserted-by":"publisher","first-page":"241","DOI":"10.18653\/v1\/W19-4825","article-title":"Open Sesame: getting inside BERT\u2019s linguistic Knowledge","volume-title":"Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","author":"Lin","year":"2019"},{"key":"2025110419273164800_bib48","doi-asserted-by":"publisher","first-page":"4129","DOI":"10.18653\/v1\/N19-1419","article-title":"A structural probe for finding syntax in word representations","volume-title":"Proceedings of the 2019 Conference of the North","author":"Hewitt","year":"2019"},{"key":"2025110419273164800_bib49","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.18653\/v1\/N19-1112","article-title":"Linguistic knowledge and transferability of contextual representations","volume-title":"Proceedings of the 2019 Conference of the North","author":"Liu","year":"2019"},{"key":"2025110419273164800_bib50","article-title":"Large batch optimization for deep learning: training BERT in 76 minutes","volume-title":"8th International Conference on Learning Representations, ICLR 2020.","author":"You","year":"2019"},{"key":"2025110419273164800_bib51","doi-asserted-by":"publisher","first-page":"4225","DOI":"10.3390\/app13074225","article-title":"Fine-tuning BERT-based pre-trained models for Arabic dependency parsing","volume":"13","author":"Al-Ghamdi","year":"2023","journal-title":"Appl Sci"},{"key":"2025110419273164800_bib52","doi-asserted-by":"publisher","first-page":"012055","DOI":"10.1088\/1742-6596\/1229\/1\/012055","article-title":"Confusion matrices and rough set data analysis","volume":"1229","author":"D\u00fcntsch","year":"2019","journal-title":"J Phys Conf Ser"},{"key":"2025110419273164800_bib53","article-title":"Understanding & interpreting confusion matrix in machine learning","author":"Bhandari","year":"2020"},{"key":"2025110419273164800_bib54","first-page":"328","article-title":"Universal language model fine-tuning for text classification","volume-title":"ACL 2018\u201356th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)","author":"Howard","year":"2018"},{"key":"2025110419273164800_bib55","article-title":"Summary of our cyberbullying research (2004-2022)","author":"Hethnawi","year":"23  2025."}],"container-title":["Journal of Cybersecurity"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/cybersecurity\/article-pdf\/11\/1\/tyaf030\/65168323\/tyaf030.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/cybersecurity\/article-pdf\/11\/1\/tyaf030\/65168323\/tyaf030.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:27:40Z","timestamp":1762302460000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/cybersecurity\/article\/doi\/10.1093\/cybsec\/tyaf030\/8313772"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1,17]]}},"URL":"https:\/\/doi.org\/10.1093\/cybsec\/tyaf030","relation":{},"ISSN":["2057-2085","2057-2093"],"issn-type":[{"value":"2057-2085","type":"print"},{"value":"2057-2093","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]},"article-number":"tyaf030"}}