{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T12:32:26Z","timestamp":1788697946030,"version":"build-2803163510"},"reference-count":37,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T00:00:00Z","timestamp":1751068800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Mexican Government","award":["A1-S-47854"],"award-info":[{"award-number":["A1-S-47854"]}]},{"name":"Mexican Government","award":["20254236"],"award-info":[{"award-number":["20254236"]}]},{"name":"Mexican Government","award":["20253468"],"award-info":[{"award-number":["20253468"]}]},{"name":"Mexican Government","award":["20254341"],"award-info":[{"award-number":["20254341"]}]},{"name":"Secretar\u00eda de Investigaci\u00f3n y Posgrado of the Instituto Polit\u00e9cnico Nacional, Mexico","award":["A1-S-47854"],"award-info":[{"award-number":["A1-S-47854"]}]},{"name":"Secretar\u00eda de Investigaci\u00f3n y Posgrado of the Instituto Polit\u00e9cnico Nacional, Mexico","award":["20254236"],"award-info":[{"award-number":["20254236"]}]},{"name":"Secretar\u00eda de Investigaci\u00f3n y Posgrado of the Instituto Polit\u00e9cnico Nacional, Mexico","award":["20253468"],"award-info":[{"award-number":["20253468"]}]},{"name":"Secretar\u00eda de Investigaci\u00f3n y Posgrado of the Instituto Polit\u00e9cnico Nacional, Mexico","award":["20254341"],"award-info":[{"award-number":["20254341"]}]},{"name":"Plataforma de Aprendizaje Profundo para Tecnolog\u00edas del Lenguaje of the Laboratorio de Superc\u00f3mputo of the INAOE, Mexico","award":["A1-S-47854"],"award-info":[{"award-number":["A1-S-47854"]}]},{"name":"Plataforma de Aprendizaje Profundo para Tecnolog\u00edas del Lenguaje of the Laboratorio de Superc\u00f3mputo of the INAOE, Mexico","award":["20254236"],"award-info":[{"award-number":["20254236"]}]},{"name":"Plataforma de Aprendizaje Profundo para Tecnolog\u00edas del Lenguaje of the Laboratorio de Superc\u00f3mputo of the INAOE, Mexico","award":["20253468"],"award-info":[{"award-number":["20253468"]}]},{"name":"Plataforma de Aprendizaje Profundo para Tecnolog\u00edas del Lenguaje of the Laboratorio de Superc\u00f3mputo of the INAOE, Mexico","award":["20254341"],"award-info":[{"award-number":["20254341"]}]},{"name":"Microsoft Latin America PhD Award","award":["A1-S-47854"],"award-info":[{"award-number":["A1-S-47854"]}]},{"name":"Microsoft Latin America PhD Award","award":["20254236"],"award-info":[{"award-number":["20254236"]}]},{"name":"Microsoft Latin America PhD Award","award":["20253468"],"award-info":[{"award-number":["20253468"]}]},{"name":"Microsoft Latin America PhD Award","award":["20254341"],"award-info":[{"award-number":["20254341"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>The detection of abusive language in Roman Urdu is important for secure digital interaction. This work investigates machine learning (ML), deep learning (DL), and transformer-based methods for detecting offensive language in Roman Urdu comments collected from YouTube news channels. Extracted features use TF-IDF and Count Vectorizer for unigrams, bigrams, and trigrams. Of all the ML models\u2014Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Na\u00efve Bayes (NB)\u2014the best performance was achieved by the same SVM. DL models involved evaluating Bi-LSTM and CNN models, where the CNN model outperformed the others. Moreover, transformer variants such as LLaMA 2 and ModernBERT (MBERT) were instantiated and fine-tuned with LoRA (Low-Rank Adaptation) for better efficiency. LoRA has been tuned for large language models (LLMs), a family of advanced machine learning frameworks, based on the principle of making the process efficient with extremely low computational cost with better enhancement. According to the experimental results, LLaMA 2 with LoRA attained the highest F1-score of 96.58%, greatly exceeding the performance of other approaches. To elaborate, LoRA-optimized transformers perform well in capturing detailed subtleties of linguistic nuances, lending themselves well to Roman Urdu offensive language detection. The study compares the performance of conventional and contemporary NLP methods, highlighting the relevance of effective fine-tuning methods. Our findings pave the way for scalable and accurate automated moderation systems for online platforms supporting multiple languages.<\/jats:p>","DOI":"10.3390\/a18070396","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T12:10:31Z","timestamp":1751285431000},"page":"396","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["RU-OLD: A Comprehensive Analysis of Offensive Language Detection in Roman Urdu Using Hybrid Machine Learning, Deep Learning, and Transformer Models"],"prefix":"10.3390","volume":"18","author":[{"given":"Muhammad","family":"Zain","sequence":"first","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Av. Juan de Dios Batiz, s\/n, Mexico City 07320, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2877-8135","authenticated-orcid":false,"given":"Nisar","family":"Hussain","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Av. Juan de Dios Batiz, s\/n, Mexico City 07320, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7536-6969","authenticated-orcid":false,"given":"Amna","family":"Qasim","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Av. Juan de Dios Batiz, s\/n, Mexico City 07320, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gull","family":"Mehak","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Av. Juan de Dios Batiz, s\/n, Mexico City 07320, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fiaz","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Central Punjab, Punjab 54810, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3901-3522","authenticated-orcid":false,"given":"Grigori","family":"Sidorov","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Av. Juan de Dios Batiz, s\/n, Mexico City 07320, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7845-9039","authenticated-orcid":false,"given":"Alexander","family":"Gelbukh","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Av. Juan de Dios Batiz, s\/n, Mexico City 07320, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Caselli, T., Basile, V., Mitrovi\u0107, J., and Granitzer, M. (2020). HateBERT: Retraining BERT for abusive language detection in English. arXiv.","DOI":"10.18653\/v1\/2021.woah-1.3"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Clarke, C., Hall, M., Mittal, G., Yu, Y., Sajeev, S., Mars, J., and Chen, M. (2023). Rule by example: Harnessing logical rules for explainable hate speech detection. arXiv.","DOI":"10.1142\/S2972335324500030"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3609","DOI":"10.1007\/s13369-023-08100-4","article-title":"Data augmentation for improving explainability of hate speech detection","volume":"49","author":"Ansari","year":"2024","journal-title":"Arab. J. Sci. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ferrer, R., Ali, K., and Hughes, C. (2024). Using AI-based virtual companions to assist adolescents with autism in recognizing and addressing cyberbullying. Sensors, 24.","DOI":"10.3390\/s24123875"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hussain, N., Qasim, A., Mehak, G., Kolesnikova, O., Gelbukh, A., and Sidorov, G. (2025). ORUD-Detect: A Comprehensive Approach to Offensive Language Detection in Roman Urdu Using Hybrid Machine Learning\u2013Deep Learning Models with Embedding Techniques. Information, 16.","DOI":"10.3390\/info16020139"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2893","DOI":"10.1007\/s40747-022-00693-x","article-title":"Evaluating feature combination strategies for hate-speech detection in Spanish using linguistic features and transformers","volume":"9","year":"2023","journal-title":"Complex Intell. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Garc\u00eda-D\u00edaz, J.A., Pan, R., and Valencia-Garc\u00eda, R. (2023). Leveraging zero and few-shot learning for enhanced model generality in hate speech detection in Spanish and English. Mathematics, 11.","DOI":"10.3390\/math11245004"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hussain, N., Qasim, A., Mehak, G., Kolesnikova, O., Gelbukh, A., and Sidorov, G. (2025). Hybrid Machine Learning and Deep Learning Approaches for Insult Detection in Roman Urdu Text. AI, 6.","DOI":"10.3390\/ai6020033"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"18395","DOI":"10.1007\/s00521-023-08657-z","article-title":"Hatdo: Hybrid Archimedes Tasmanian Devil Optimization CNN for classifying offensive comments and non-offensive comments","volume":"35","author":"Aarthi","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_10","first-page":"9","article-title":"Development of a novel approach to search resources in IoT","volume":"9","author":"Hussain","year":"2018","journal-title":"Development"},{"key":"ref_11","first-page":"469","article-title":"Towards a cyberbullying detection approach: Fine-tuned contrastive self-supervised learning for data augmentation","volume":"19","author":"Moradpoor","year":"2024","journal-title":"Int. J. Data Sci. Anal."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"32","DOI":"10.5815\/ijmecs.2019.07.04","article-title":"Sentiment analysis on mobile phone reviews using supervised learning techniques","volume":"10","author":"Shaheen","year":"2019","journal-title":"Int. J. Mod. Educ. Comput. Sci."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Almaliki, M., Almars, A.M., Gad, I., and Atlam, E.-S. (2023). ABMM: Arabic BERT-mini model for hate-speech detection on social media. Electronics, 12.","DOI":"10.3390\/electronics12041048"},{"key":"ref_14","first-page":"1031","article-title":"Offensive Language and Hate Speech Detection Using Transformers and Ensemble Learning Approaches","volume":"28","author":"Aklouche","year":"2024","journal-title":"Comput. Sist."},{"key":"ref_15","first-page":"972","article-title":"BERT-based approach to Arabic hate speech and offensive language detection in Twitter: Exploiting emojis and sentiment analysis","volume":"13","author":"Althobaiti","year":"2022","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"86252","DOI":"10.1109\/ACCESS.2024.3415350","article-title":"SO-Hatred: A novel hybrid system for Turkish hate speech detection in social media with ensemble deep learning improved by BERT and clustered-graph networks","volume":"12","author":"Altinel","year":"2024","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Qasim, A., Mehak, G., Hussain, N., Gelbukh, A., and Sidorov, G. (2025). Detection of Depression Severity in Social Media Text Using Transformer-Based Models. Information, 16.","DOI":"10.3390\/info16020114"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1007\/s10579-023-09642-7","article-title":"UHateD: Hate speech detection in Urdu language using transfer learning","volume":"57","author":"Arshad","year":"2023","journal-title":"Lang. Resour. Eval."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s13677-024-00600-4","article-title":"Graph convolution networks for social media trolls detection using deep feature extraction","volume":"13","author":"Asif","year":"2024","journal-title":"J. Cloud Comput."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"11441","DOI":"10.1038\/s41598-023-38171-0","article-title":"Machine Learning-Based Guilt Detection in Text","volume":"13","author":"Meque","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Bilal, M., Khan, A., Jan, S., Musa, S., and Ali, S. (2023). Roman Urdu hate speech detection using transformer-based model for cyber security applications. Sensors, 23.","DOI":"10.3390\/s23083909"},{"key":"ref_22","first-page":"681","article-title":"Comparing Pre-Trained Language Model for Arabic Hate Speech Detection","volume":"28","author":"Daouadi","year":"2024","journal-title":"Comput. Sist."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1727","DOI":"10.1007\/s10964-016-0541-z","article-title":"Peer cybervictimization among adolescents and the associated internalizing and externalizing problems: A meta-analysis","volume":"45","author":"Fisher","year":"2016","journal-title":"J. Youth Adolesc."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3232676","article-title":"A survey on automatic detection of hate speech in text","volume":"51","author":"Fortuna","year":"2018","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3501398","article-title":"Investigating the effect of preprocessing Arabic text on offensive language and hate speech detection","volume":"21","author":"Husain","year":"2022","journal-title":"Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"79697","DOI":"10.1109\/ACCESS.2023.3299021","article-title":"G-BERT: An efficient method for identifying hate speech in Bengali texts on social media","volume":"11","author":"Keya","year":"2023","journal-title":"IEEE Access"},{"key":"ref_27","unstructured":"Mehak, G., Qasim, A., Meque, A.G.M., Hussain, N., Sidorov, G., and Gelbukh, A. (2025, January 19). TechExperts (IPN) at GenAI Detection Task 1: Detecting AI-Generated Text in English and Multilingual Contexts. Proceedings of the 1st Workshop on GenAI Content Detection (GenAIDetect), Abu Dhabi, United Arab Emirates."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"19755","DOI":"10.1109\/ACCESS.2025.3534662","article-title":"An automatic approach for the identification of offensive language in Perso-Arabic Urdu Language: Dataset Creation and Evaluation","volume":"13","author":"Din","year":"2025","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1016\/j.procs.2025.03.214","article-title":"Detection of Abusive Language for YouTube Comments in Urdu and Roman Urdu using CLSTM Model","volume":"260","author":"Rajput","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"21853","DOI":"10.1109\/ACCESS.2025.3532611","article-title":"UEF-HOCUrdu: Unified Embeddings Ensemble Framework for Hate and Offensive Text Classification in Urdu","volume":"13","author":"Ullah","year":"2025","journal-title":"IEEE Access"},{"key":"ref_31","unstructured":"Alvi, M., Alvi, M.B., and Fatima, N. (2025). A Framework for Sarcasm Detection Incorporating Roman Sindhi and Roman Urdu Scripts in Multilingual Dataset Analysis. J. Comput. Biomed. Inform., 8."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Hussain, N., Qasim, A., Akhtar, Z.U.D., Qasim, A., Mehak, G., del Socorro Espindola Ulibarri, L., and Gelbukh, A. (2023). Stock Market Performance Analytics Using XGBoost. Proceedings of the Mexican International Conference on Artificial Intelligence, Springer Nature.","DOI":"10.1007\/978-3-031-47765-2_1"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"21635","DOI":"10.1109\/ACCESS.2025.3535862","article-title":"Urdu Toxic Comment Classification with PURUTT Corpus Development","volume":"13","author":"Saeed","year":"2025","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Naseeb, A., Zain, M., Hussain, N., Qasim, A., Ahmad, F., Sidorov, G., and Gelbukh, A. (2025). Machine Learning- and Deep Learning-Based Multi-Model System for Hate Speech Detection on Facebook. Algorithms, 18.","DOI":"10.3390\/a18060331"},{"key":"ref_35","unstructured":"Islam, M., Khan, J.A., Abaker, M., Daud, A., and Irshad, A. (2025). Unified Large Language Models for Misinformation Detection in Low-Resource Linguistic Settings. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3711710","article-title":"Hate Speech Detection Research in South Asian Languages: A Survey of Tasks, Datasets and Methods","volume":"24","author":"Sharma","year":"2025","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"ref_37","unstructured":"Alansari, A., and Luqman, H. (2025). Multi-task Learning with Active Learning for Arabic Offensive Speech Detection. arXiv."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/7\/396\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:00:53Z","timestamp":1760032853000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/7\/396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,28]]},"references-count":37,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["a18070396"],"URL":"https:\/\/doi.org\/10.3390\/a18070396","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,28]]}}}