ADVANCED DEEP-LEARNING TECHNIQUES FOR IMPROVED CYBERBULLYING DETECTION IN ARABIC TWEETS

(Received: 1-Mar.-2025, Revised: 11-May-2025 and 15-Jun.-2025 , Accepted: 19-Jun.-2025)

Authors Marah Hawa, Thani Kmail, Ahmad Hasasneh,

Keywords #Machine learning algorithms #Arabic tweets #Deep-learning techniques #Recurrent neural network #Cyberbullying

Abstract Cyberbullying has emerged as a pressing issue in the digital era, particularly within Arabic-speaking communities, where research remains limited. This study investigates the detection of Arabic cyberbullying on social media using both traditional machine learning (ML) and deep learning (DL) techniques. A publicly available dataset of Arabic tweets was used to train and evaluate several ML models (SVM, NB, LR and XGBoost), alongside a recurrent neural network (RNN). The results demonstrate that the RNN significantly outperforms classical ML models, highlighting the efficacy of DL in accurately identifying abusive content in Arabic text. These results emphasize the necessity of incorporating linguistically rich data and advanced neural architectures to improve cyberbullying-detection systems in low-resource languages such as Arabic.

References

[1] W. N. H. Wan Ali, M. Mohd and F. Fauzi, "Cyberbullying Detection: An Overview," Proc. of the 2018Cyber Resilience Conf. (CRC), pp. 1–6, DOI: 10.1109/CR.2018.8626869, Putrajaya, Malaysia, 2018.

[2] B. Srinandhini and J. I. Sheeba, "Online Social Network Bullying Detection Using IntelligenceTechniques," Procedia Computer Science, vol. 45, pp. 485–492, DOI:10.1016/j.procs.2015.03.085, 2015.

[3] TechJury, "50 Alarming Cyberbullying Statistics to Know in 2024," [Online], Available:https://techjury.net/blog/cyberbullying-statistics/, Accessed: Jan. 2, 2025.

[4] Cyberbullying Research Center, "2023 Cyberbullying Data - Cyberbullying Research Center," [Online],Available: https://cyberbullying.org/2023-cyberbullying-data, Accessed: Aug. 27, 2024.

[5] Statista, "COVID-19 Vaccine: Adverse Events by Age and Gender in Spain," [Online], Available:https://www.statista.com/statistics/1220543/covid-19-vaccine-number-of-adverse-events-reported-by-age-and-gender-spain/, Accessed: May 10, 2025.

[6] UNICEF, "Search | UNICEF," [Online], Available: https://www.unicef.org/search?query=Statistic+cybeRbullying, Accessed: May 10, 2025.

[7] 7amleh, "7amleh - Annual Report 2023," [Online], Available: https://7amleh.org/annual23/eng/, Accessed: May 10, 2025.

[8] Ditch the Label, "Youth Charity | Mental Health, Bullying & Relationships," [Online], Available: https://www.ditchthelabel.org/cyber-bullying-statistics-what-they-tell-us, Accessed: Aug. 27, 2024.

[9] D. Musleh et al., "A Machine Learning Approach to Cyberbullying Detection in Arabic Tweets," Computers, Materials and Continua, vol. 80, no. 1, pp. 1033–1054, Jul. 2024.

[10] Statista, "Most Used Languages Online by Share of Websites 2024," [Online], Available: https://www.statista.com/statistics/262946/most-common-languages-on-the-internet/, Aug., 2024.

[11] A. Alqarni and A. Rahman, "Arabic Tweets-based Sentiment Analysis to Investigate the Impact of COVID-19 in KSA: A Deep Learning Approach," Big Data and Cognitive Computing, vol. 7, no. 1, p. 16, DOI: 10.3390/bdcc7010016, Jan. 2023.

[12] W. J. Hutchins, "The Georgetown-IBM Experiment Demonstrated in January 1954," Lecture Notes in Computer Science, vol. 3265, pp. 102–114, DOI: 10.1007/978-3-540-30194-3_12, 2004.

[13] A. Mandal, "Evolution of Machine Translation," Towards Data Science, [Online], Available: https://towardsdatascience.com/evolution-of-machine-translation-5524f1c88b25, Aug. 27, 2024.

[14] S. Almutiry, M. Abdel Fattah and S. Arabia-Almadinah Almunawarah, "Arabic CyberBullying Detection Using Arabic Sentiment Analysis," Egyptian Journal of Language Eng., vol. 8, no. 1, pp. 39–50, 2021.

[15] T. Kanan, A. Aldaaja and B. Hawashin, "Cyber-Bullying and Cyber-Harassment Detection Using Supervised Machine Learning Techniques in Arabic Social Media Contents," Journal of Internet Technology, vol. 21, no. 5, pp. 1409–1421, DOI: 10.3966/160792642020092105016, Sep. 2020.

[16] I. Abu El-Khair, "Effects of Stop Words Elimination on Arabic Information Retrieval," International Journal of Computing & Information Sciences, vol. 4, no. 3, pp. 119–133, 2006.

[17] M. A. Al-Ajlan and M. Ykhlef, "Deep Learning Algorithm for Cyberbullying Detection," Int. J. of Advanced Computer Science and Applications, vol. 9, no. 9, pp. 199-205, 2018.

[18] B. Haidar, M. Chamoun and A. Serhrouchni, "Arabic Cyberbullying Detection: Using Deep Learning," Proc. of the 2018 7th Int. Conf. on Computer and Communication Engineering (ICCCE), pp. 284–289, DOI: 10.1109/ICCCE.2018.8539303, Kuala Lumpur, Malaysia, Nov. 2018.

[19] B. Haidar, M. Chamoun and A. Serhrouchni, "A Multilingual System for Cyberbullying Detection: Arabic Content Detection Using Machine Learning," Advances in Science, Technology and Engineering Systems J., vol. 2, no. 6, pp. 275–284, DOI: 10.25046/AJ020634, 2017.

[20] B. Y. Alharbi et al., "Automatic Cyber Bullying Detection in Arabic Social Media," Int. J. of Engineering Research & Technology, vol. 12, pp. 2330–2335, 2019.

[21] D. Mouheb et al., "Detection of Arabic Cyberbullying on Social Networks Using Machine Learning," Proc. of the 2019 IEEE/ACS 16th Int. Conf. on Computer Systems and Applications (AICCSA), DOI: 10.1109/AICCSA47632.2019.9035276, Abu Dhabi, UAE, Nov. 2019.

[22] K. Reynolds et al., "Using Machine Learning to Detect Cyberbullying," Proc. of the 10th Int'l Conf. Mach. Learn. Appl. (ICMLA), vol. 2, pp. 241–244, DOI: 10.1109/ICMLA.2011.152, Honolulu, USA, 2011.

[23] J. Hani et al., "Social Media Cyberbullying Detection Using Machine Learning," Int. J. of Advanced Computer Science and Applications, vol. 10, no. 5, pp. 703–707, 2019.

[24] B. A. Rachid et al., "Classification of Cyberbullying Text in Arabic," Proc. of the IEEE Int. Joint Conf. on Neural Networks (IJCNN), DOI: 10.1109/IJCNN48605.2020.9206643, Glasgow, UK, Jul. 2020.

[25] T. D. Alsubait, "Comparison of Machine Learning Techniques for Cyberbullying Detection on YouTube Arabic Comments," Int. J. of Computer Science and Network Security, vol. 21, no. 1, pp. 1–5, 2021.

[26] V. Banerjee et al., "Detection of Cyberbullying Using Deep Neural Network," Proc. of the IEEE 2019 5th Int. Conf. on Advanced Computing & Communication Systems (ICACCS), pp. 604–607, DOI: 10.1109/ICACCS.2019.8728378, Coimbatore, India, Mar. 2019.

[27] C. Iwendi et al., "Cyberbullying Detection Solutions Based on Deep Learning Architectures," Multimedia Systems, vol. 29, no. 3, pp. 1839–1852, DOI: 10.1007/S00530-020-00701-5, Jun. 2023.

[28] D. A. Musleh et al., "Arabic Sentiment Analysis of YouTube Comments: NLP-based Machine Learning Approaches for Content Evaluation," Big Data and Cognitive Computing, vol. 7, no. 3, p. 127, Jul. 2023.

[29] K. T. Mursi et al., "ArCyb: A Robust Machine-learning Model for Arabic Cyberbullying Tweets in Saudi Arabia," Int. J. of Advanced Computer Science and Applications, vol. 14, no. 9, pp. 1059–1067, 2023.

[30] M. Alzaqebah et al., "Cyberbullying Detection Framework for Short and Imbalanced Arabic Datasets," J. of King Saud Uni. - Computer and Information Sciences, vol. 35, no. 8, p. 101652, Sep. 2023.

[31] A. M. Alduailaj and A. Belghith, "Detecting Arabic Cyberbullying Tweets Using Machine Learning," Machine Learning and Knowledge Extraction, vol. 5, no. 1, pp. 29–42, Jan. 2023.

[32] M. Khairy et al., "Comparative Performance of Ensemble Machine Learning for Arabic Cyberbullying and Offensive Language Detection," Language Resources and Evaluation, vol. 58, no. 2, pp. 695–712, DOI: 10.1007/S10579-023-09683-Y, Jun. 2024.

[33] A. H. Zahid et al., "Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization," arXiv, arXiv: 2502.19612, Feb. 2025.

[34] A. Charfi et al., "Hate Speech Detection with ADHAR: AMulti-dialectal Hate Speech Corpus in Arabic,"Frontiers in Artificial Intelligence, vol. 7, p. 1391472, DOI: 10.3389/FRAI.2024.1391472, May 2024.

[35] A. Altayeva et al., "Hybrid Deep Learning Model for Cyberbullying Detection on Online Social MediaData," Int. J. of Computer Science, vol. 8, no. 3, Sep. 2022.

[36] A. Alhazmi et al., "Code-mixing unveiled: Enhancing the hate speech detection in Arabic dialect tweetsusing machine learning models," PLOS One, vol. 19, no. 7, p. e0305657, 2024.

[37] R. Obeidat et al., "Deep Learning vs. Traditional Machine Learning for Arabic Sentiment Analysis: AComparative Study," Int. J. of Advanced Computer Science and Appl., vol. 12, no. 4, pp. 188–195, 2021.

[38] A. Al-Hassan and H. Al-Dossari, "A Benchmark Dataset for Arabic Cyberbullying Detection on Twitter:Design and Evaluation," Int. J. of Advanced Computer Science and Appl., vol. 11, no. 2, pp. 72–78, 2020.

[39] G. Jaradat et al., "Deep Learning Approaches for Detecting Cyberbullying on Social Media," J. ofComputational and Cognitive Engineering, vol. 2025, no. 00, pp. 1–15, Mar. 2025.

[40] I. Jamaleddyn, R. El Ayachi and M. Biniz, "Novel Multi-channel Deep Learning Model for Arabic NewsClassification," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 10, no. 4, pp. 453–468, DOI: 10.5455/jjcit.71-1720086134, Dec. 2024.

[41] L. Al Qadi, H. El Rifai, S. Obaid and A. Elnagar, "A Scalable Shallow Learning Approach for TaggingArabic News Articles," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 6, no. 3, pp. 263–280, DOI: 10.5455/jjcit.71-1585409230, Sep. 2020.

[42] Haithem Hermessi, "Arabic Levantine Hate Speech Detection," [Online], Available:https://www.kaggle.com/datasets/haithemhermessi/arabic-levantine-hate-speech-detection, Jan. 2025.

[43] M. K. Saad, "Arabic Sentiment Twitter Corpus," [Online], Available: https://www.kaggle.com/datasets/
mksaad/arabic-sentiment-twitter-corpus, Jan. 2025.
[44] A. Saleh, "Arabic Dataset1," [Online], Available: https://www.kaggle.com/datasets/ahmadsaleh2001/arabicdataset1, Jan. 2025.

[45] M. Tami et al., "Transformer-based Approach to Pathology Diagnosis Using Audio Spectrogram,"Information, vol. 15, no. 5, p. 253, DOI: 10.3390/info15050253, 2024.