--- title: "REGLAT at MAHED Shared Task — paper by Ashraf et al. (2025)" description: "The REGLAT team built a system for subtask 1 of the MAHED shared task at ArabicNLP 2025. 3 references, cited by 1 paper here." authors: ["Nsrin Ashraf", "Mariam Labib", "Tarek Elshishtawy", "Hamada Nayel"] year: 2025 venue: "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks" source: "https://aclanthology.org/2025.arabicnlp-sharedtasks.88/" doi: "10.18653/v1/2025.arabicnlp-sharedtasks.88" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/ashraf-2025-reglat-mahed-shared-task-hybrid/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ashraf-2025-reglat-mahed-shared-task-hybrid/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/16/) / REGLAT at MAHED Shared Task: A Hybrid Ensemble-Based System for Arabic Hate Speech Detection # REGLAT at MAHED Shared Task: A Hybrid Ensemble-Based System for Arabic Hate Speech Detection **Authors:** [Nsrin Ashraf](https://md.research.elamur.ai/free/en/authors/nsrin-ashraf/), [Mariam Labib](https://md.research.elamur.ai/free/en/authors/mariam-labib/), [Tarek Elshishtawy](https://md.research.elamur.ai/free/en/authors/tarek-elshishtawy/) and [Hamada Nayel](https://md.research.elamur.ai/free/en/authors/hamada-nayel/) · **Year:** 2025 · **Venue:** [Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks](https://md.research.elamur.ai/free/en/venues/arabicnlp/) ([ArabicNLP 2025](https://md.research.elamur.ai/free/en/venues/arabicnlp/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2025.arabicnlp-sharedtasks.88/) · [PDF](https://aclanthology.org/2025.arabicnlp-sharedtasks.88.pdf) · [DOI 10.18653/v1/2025.arabicnlp-sharedtasks.88](https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.88) · [OpenAlex](https://openalex.org/W4416037641) **Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/ashraf-2025-reglat-mahed-shared-task-hybrid/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary The REGLAT team built a system for subtask 1 of the MAHED shared task at ArabicNLP 2025. The subtask asks for social media posts in Arabic dialects and MSA to be sorted into three classes: Hate, Hope, or Not Applicable. The organizers supplied manually annotated data, already divided into training, validation, and test portions. The authors cleaned the text with regex and NLTK, then compared several families of models: - sparse TF-IDF features fed to SVM and Logistic Regression; - a CNN-BiLSTM network using either AraVec or GloVe embeddings; - fine-tuned AraBERTv2 and CAMeLBERT. Their final system combines the predictions of a TF-IDF + Logistic Regression model and a fine-tuned AraBERTv2 model through majority voting. This hybrid reached a macro F1 of 0.58, clearly above any single model; the best standalone result was AraBERTv2 at 0.46. The main lesson is that a simple linear model over n-grams still adds value next to a transformer. Combining lexical and contextual signals is a cheap way to gain accuracy on imbalanced, dialect-rich classification. ## Key points - The data is MAHED subtask 1, with labels Hate, Hope, and Not Applicable. The organizers split it 70/15/15 into train, validation, and test, and the official metric is macro F1 because the classes are imbalanced. - Preprocessing removes URLs, mentions, punctuation, symbols, emojis, Latin letters, and digits, and normalizes Arabic letters. - Single-model macro F1 scores: - SVM (TF-IDF): 0.42 - LR (TF-IDF): 0.40 - AraBERTv2: 0.46 - CAMeLBERT: 0.36 - CNN-BiLSTM with AraVec (300d): 0.31 - CNN-BiLSTM with GloVe (200d): 0.12 - Hybrid macro F1 scores: - LR-AraBERTv2: 0.58 (best) - LR-CAMeLBERT: 0.54 - SVM-AraBERTv2: 0.47 - SVM-CAMeLBERT: 0.44 - Settings: - TF-IDF: 1–3-grams, at most 50,000 features, min_df 5, max_df 0.9, sublinear tf. - LR: class_weight balanced. - AraBERTv2: AdamW, learning rate 2e-5, batch size 16, 3 epochs. - Hardware: a Colab T4 GPU. ## Interesting ideas - Combining a sparse n-gram linear model with a contextual transformer beat both of them (0.58 vs 0.40 and 0.46), so the two models evidently make different mistakes. - The best partner for the transformer was not the strongest solo model: LR scored below SVM on its own but produced the better hybrid. - The authors handled a skewed label set, where a catch-all "Not Applicable" class dominates, with balanced class weights and macro F1, so rare classes count fully. - A language-specific embedding (AraVec) far outperformed a general-purpose one (GloVe) inside the same architecture (0.31 vs 0.12), showing that resource match can matter more than model design. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (learn): when assembling witness parsers for silver data, include a deliberately cheap, feature-based witness next to gparse, so that agreement draws on genuinely different error profiles. - **I2** (learn): choose the set of witnesses or teachers by measuring how the combined ensemble scores on dev data, not by ranking each candidate's individual LAS. - **I3** (frames): speech-act and irony labels are similarly rare, so classifiers for them should use class weighting and be reported with macro F1 rather than accuracy. - **I4** (tokens): before tuning the tagger's architecture, check whether the lexical resources and embeddings actually match the genre being processed, such as school texts or fables. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Prince Sattam Bin Abdulaziz University](https://md.research.elamur.ai/free/en/universities/prince-sattam-bin-abdulaziz-university/) — University, Al Kharj, Saudi Arabia · 17 works · 489 citations - [Benha University](https://md.research.elamur.ai/free/en/universities/benha-university/) — University, Banhā, Egypt · 14 works · 89 citations - [ElSewedy University of Technology](https://md.research.elamur.ai/free/en/universities/elsewedy-university-of-technology/) — University, Cairo, Egypt · 5 works · 5 citations - [Mansoura University](https://md.research.elamur.ai/free/en/universities/mansoura-university/) — University, Al Mansurah, Egypt · 4 works · 260 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 626 works 🧭 Topics (3): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 1,035 works · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 3,066 works · [🛡️ Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · 587 works ## Cite Cite as: Nsrin Ashraf, Mariam Labib, Tarek Elshishtawy and Hamada Nayel. 2025. REGLAT at MAHED Shared Task: A Hybrid Ensemble-Based System for Arabic Hate Speech Detection. Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{ashraf2025reglat, title = {{REGLAT at MAHED Shared Task: A Hybrid Ensemble-Based System for Arabic Hate Speech Detection}}, author = {Nsrin Ashraf, Mariam Labib, Tarek Elshishtawy and Hamada Nayel}, booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks}, year = {2025}, doi = {10.18653/v1/2025.arabicnlp-sharedtasks.88}, url = {https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.88} } ``` - [← previous Regional Distribution of the /el/-/æl/ Merger in Australian English](https://md.research.elamur.ai/free/en/papers/coats-2025-regional-distribution-el-l-merger/) - [next → Reinforcing Stereotypes of Anger: Emotion AI on African American Vernacular English](https://md.research.elamur.ai/free/en/papers/dorn-2025-reinforcing-stereotypes-anger-emotion-ai/) - [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/16/) ## References 3 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Macro F1-score Ahmed Abdelali, Sabit Hassan, Hamdy Mubarak, Kareem Darwish, and Younes Samih. 2021. [Pre-training bert on arabic tweets: Practical considerations](https://md.research.elamur.ai/free/en/papers/abdelali-2021-pre-training-bert-arabic-tweets/). Preprint, arXiv:2102.10684. [↗](https://arxiv.org/abs/2102.10684) 2. Mahmoud Mohamed Abdelsamie, Shahira Shaaban Azab, and Hesham A. Hefny. 2026. The dialects gap: A multi-task learning approach for enhancing hate speech detection in arabic dialects. Expert Systems with Applications, 295:128584. [find](https://scholar.google.com/scholar?q=Mahmoud+Mohamed+Abdelsamie%2C+Shahira+Shaaban+Azab%2C+and+Hesham+A%2E+Hefny%2E+2026%2E+The+dialects+gap%3A+A+multi%2Dtask+learning+approach+for+enhancing+hate+speech+detection+in+arabic+dialects%2E+Expert+Systems+wit) 3. Muhammad Abdul-Mageed, AbdelRahim Elmadany, and El Moatez Billah Nagoudi. 2021. [ARBERT & MARBERT: Deep bidirectional transformers for Arabic](https://md.research.elamur.ai/free/en/papers/abdul-mageed-2021-arbert-marbert-deep-bidirectional-transformers/). In 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), pages 7088–7105, Online. Association for Computational Linguistics. *Table 2: System performance results on MAHED dataset* Ahmed H. AbuElAtta, Mahmoud Sobhy, Ahmed A. El-Sawy, and Hamada Nayel. 2023. Arabic regional dialect identification (ardi) using pair of continuous bag-of-words and data augmentation. International Journal of Advanced Computer Science and Applications, 14(11). *Updated 2 November 2026*