JCEEES
Journal of Computer & Electrical and Electronics Engineering Sciences

JCEEES aims to publish original articles covering the theoretical foundations of major computer, electronic and electrical engineering sciences, as well as academic, commercial and educational aspects that propose new ideas for the application and design of artificial intelligence, software and information systems. In addition to wide-ranging regular topics, JCEEES also makes it a principle to include special topics covering specific topics in all areas of interest mainly in computational medicine, artificial intelligence, computer science, and electrical & electronic engineering science.

eISSN: 2980-177X
Creative Commons CC BY-NC-ND 4.0 International License.

Online Manuscript System

Index
Original Article
Android application for multilingual hate speech detection: using XLM-RoBERTa and ONNX optimized
Abstract
Aims: Social media and digital platforms face increasing challenges in dealing with multilingual abusive content, which calls for the development of effective solutions for the automatic detection of hate speech. This research presents a practical system for monitoring hate speech in three languages (Arabic, Turkish, and English) based on the improved XLM-RoBERTa model, while exploring ensemble techniques as a baseline for comparison.
Methods: FrancophonIA data, consisting of 220,000 texts across the three languages, was used after processing. Baseline models were developed combining Logistic Regression, Support Vector Machines, and Random Forest using soft voting with TF-IDF feature extraction. The main model was based on XLM-RoBERTa with GPU-accelerated training and an early stop strategy to improve efficiency. The final models were converted to ONNX for compatibility, and a mobile application was created for Android application.
Results: The baseline model achieved a macro F1-score of 0.5827, outperforming the individual classifiers. In contrast, the optimized XLM-RoBERTa achieved a substantial improvement of 72.3% accuracy and an macro F1-score of 0.7079 across different languages. Optimization via ONNX enabled efficient real-time inference in both the API and the mobile application.
Conclusion: The research proves the feasibility of employing transformer-based multilingual models in building practical content monitoring systems, with the potential for actual deployment on mobile devices to achieve real-time monitoring of hate speech in real-world environments.

Keywords : Multilingual hate speech detection, XLM-RoBERTa, ensemble baseline, ONNX, android deployment

Download Article


1. Ahmad, A., Azzeh, M., Alnagi, E., Abu Al-Haija, Q., Halabi, D., ..., & AbuHour, Y. (2024). Hate speech detection in the Arabic language: corpus design, construction, and evaluation. Frontiers in Artificial Intelligence, 7, 1345445. https://doi.org/10.3389/frai.2024.1345445
2. Barkhordar, E., Topçu, I. S., & Hürriyetoğlu, A. (2024). Team Curie at HSD-2Lang 2024: hate speech detection in Turkish and Arabic tweets using BERT-based models. In A. Hürriyetoğlu, H. Tanev, S. Thapa, & G. Uludoğan (Eds.), Proceedings of the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2024) (pp. 215-220). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.case-1.30
3. Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., ..., & Stoyanov, V. (2020). Unsupervised cross-lingual representation learning at scale. In D. Jurafsky, J. Chai, N. Schluter, & J. Tetreault (Eds.), Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 8440-8451). Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.747
4. European Union Agency for Fundamental Rights. (2023). Online content moderation: current challenges in detecting hate speech. Publications Office of the European Union. https://doi.org/10.2811/923316
5. Mahajan, E., Mahajan, H., & Kumar, S. (2024). EnsMulHateCyb: multilingual hate speech and cyberbully detection in online social media. Expert Systems with Applications, 236, 121228. https://doi.org/10.1016/j.eswa.2023.121228
6. Mnassri, K., Farahbakhsh, R., Chalehchaleh, R., Rajapaksha, P., Jafari, A. R., ..., & Crespi, N. (2024). A survey on multi-lingual offensive language detection. PeerJ Computer Science, 10, e1934. https://doi.org/10.7717/peerj-cs.1934
7. Rust, P., Pfeiffer, J., Vulic, I., Ruder, S., & Gurevych, I. (2021). How good is your tokenizer? On the monolingual performance of multilingual language models. In C. Zong, F. Xia, W. Li, & R. Navigli (Eds.), Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (pp. 3118-3135). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.acl-long.243
8. Usman, M., Ahmad, M., Tash, M. S., Gelbukh, I., Tellez, R. Q., & Sidorov, G. (2025). Multilingual hate speech detection in social media using translation-based approaches with large language models. arXiv. https://doi.org/10.48550/arXiv.2506.08147
9. Vogels, E. A. (2021, January 13). The state of online harassment. Pew Research Center. https://www.pewresearch.org/internet/2021/01/13/the-state-of-online-harassment/
Article available in :
Volume 4, Issue 2, 2026
Page : 72-76
https://doi.org/10.51271/JCEEES-0039
Article Information
Received : 01 Şub 2026
Accepted : 07 May 2026
Published : 13 Eki 2026
Corresponding Author :

Salam Thabet Doghmash: Computer Science Major, Informatics Institute, Gazi University, Ankara, Turkiye

[email protected]
Citation : Doghmash, S. T., Doğru, İ. A., & Kılıç, K. (2026). Android application for multilingual hate speech detection: using XLM-RoBERTa and ONNX optimized. J Comp Electr Electron Eng Sci, 4(2), 72-76. https://doi.org/10.51271/JCEEES-0039

Read: 6
Download : 4
Cited: 0
_Footer