eprintid: 15444 rev_number: 9 eprint_status: archive userid: 2 dir: disk0/00/01/54/44 datestamp: 2024-11-28 23:30:21 lastmod: 2024-11-28 23:30:22 status_changed: 2024-11-28 23:30:21 type: article metadata_visibility: show creators_name: Ashiq, Waqar creators_name: Kanwal, Samra creators_name: Rafique, Adnan creators_name: Waqas, Muhammad creators_name: Khurshaid, Tahir creators_name: Caro Montero, Elizabeth creators_name: Bustamante Alonso, Alicia creators_name: Ashraf, Imran creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: elizabeth.caro@uneatlantico.es creators_id: alicia.bustamante@uneatlantico.es creators_id: title: Roman urdu hate speech detection using hybrid machine learning models and hyperparameter optimization ispublished: pub subjects: uneat_eng divisions: uneatlantico_produccion_cientifica divisions: uninimx_produccion_cientifica divisions: uninipr_produccion_cientifica divisions: unic_produccion_cientifica divisions: uniromana_produccion_cientifica full_text_status: public keywords: s Hate speech detection, Deep learning, Model optimization, Urdu text classification abstract: With the rapid increase of users over social media, cyberbullying, and hate speech problems have arisen over the past years. Automatic hate speech detection (HSD) from text is an emerging research problem in natural language processing (NLP). Researchers developed various approaches to solve the automatic hate speech detection problem using different corpora in various languages, however, research on the Urdu language is rather scarce. This study aims to address the HSD task on Twitter using Roman Urdu text. The contribution of this research is the development of a hybrid model for Roman Urdu HSD, which has not been previously explored. The novel hybrid model integrates deep learning (DL) and transformer models for automatic feature extraction, combined with machine learning algorithms (MLAs) for classification. To further enhance model performance, we employ several hyperparameter optimization (HPO) techniques, including Grid Search (GS), Randomized Search (RS), and Bayesian Optimization with Gaussian Processes (BOGP). Evaluation is carried out on two publicly available benchmarks Roman Urdu corpora comprising HS-RU-20 corpus and RUHSOLD hate speech corpus. Results demonstrate that the Multilingual BERT (MBERT) feature learner, paired with a Support Vector Machine (SVM) classifier and optimized using RS, achieves state-of-the-art performance. On the HS-RU-20 corpus, this model attained an accuracy of 0.93 and an F1 score of 0.95 for the Neutral-Hostile classification task, and an accuracy of 0.89 with an F1 score of 0.88 for the Hate Speech-Offensive task. On the RUHSOLD corpus, the same model achieved an accuracy of 0.95 and an F1 score of 0.94 for the Coarse-grained task, alongside an accuracy of 0.87 and an F1 score of 0.84 for the Fine-grained task. These results demonstrate the effectiveness of our hybrid approach for Roman Urdu hate speech detection. date: 2024-11 publication: Scientific Reports volume: 14 number: 1 id_number: doi:10.1038/s41598-024-79106-7 refereed: TRUE issn: 2045-2322 official_url: http://doi.org/10.1038/s41598-024-79106-7 access: open language: en citation: Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Producción Científica Universidad Internacional Iberoamericana Puerto Rico > Investigación > Artículos y libros Universidad Internacional do Cuanza > Investigación > Producción Científica Universidad de La Romana > Investigación > Producción Científica Abierto Inglés With the rapid increase of users over social media, cyberbullying, and hate speech problems have arisen over the past years. Automatic hate speech detection (HSD) from text is an emerging research problem in natural language processing (NLP). Researchers developed various approaches to solve the automatic hate speech detection problem using different corpora in various languages, however, research on the Urdu language is rather scarce. This study aims to address the HSD task on Twitter using Roman Urdu text. The contribution of this research is the development of a hybrid model for Roman Urdu HSD, which has not been previously explored. The novel hybrid model integrates deep learning (DL) and transformer models for automatic feature extraction, combined with machine learning algorithms (MLAs) for classification. To further enhance model performance, we employ several hyperparameter optimization (HPO) techniques, including Grid Search (GS), Randomized Search (RS), and Bayesian Optimization with Gaussian Processes (BOGP). Evaluation is carried out on two publicly available benchmarks Roman Urdu corpora comprising HS-RU-20 corpus and RUHSOLD hate speech corpus. Results demonstrate that the Multilingual BERT (MBERT) feature learner, paired with a Support Vector Machine (SVM) classifier and optimized using RS, achieves state-of-the-art performance. On the HS-RU-20 corpus, this model attained an accuracy of 0.93 and an F1 score of 0.95 for the Neutral-Hostile classification task, and an accuracy of 0.89 with an F1 score of 0.88 for the Hate Speech-Offensive task. On the RUHSOLD corpus, the same model achieved an accuracy of 0.95 and an F1 score of 0.94 for the Coarse-grained task, alongside an accuracy of 0.87 and an F1 score of 0.84 for the Fine-grained task. These results demonstrate the effectiveness of our hybrid approach for Roman Urdu hate speech detection. metadata Ashiq, Waqar; Kanwal, Samra; Rafique, Adnan; Waqas, Muhammad; Khurshaid, Tahir; Caro Montero, Elizabeth; Bustamante Alonso, Alicia y Ashraf, Imran mail SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, elizabeth.caro@uneatlantico.es, alicia.bustamante@uneatlantico.es, SIN ESPECIFICAR (2024) Roman urdu hate speech detection using hybrid machine learning models and hyperparameter optimization. Scientific Reports, 14 (1). ISSN 2045-2322 document_url: http://repositorio.unib.org/id/eprint/15444/1/s41598-024-79106-7.pdf