{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T23:20:16Z","timestamp":1768951216272,"version":"3.49.0"},"reference-count":27,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study aims to develop an automatic system for detecting toxic comments in online environments, particularly on social networking platforms. The focus is on efficiently identifying and categorizing toxicity in user-generated comments to address the growing issue of harmful online content. A novel hybrid model, Text-BGRU-CNN, combining Bidirectional Gated Recurrent Unit (BGRU) and Text Convolutional Neural Network (Text-CNN), is introduced for multilabel toxicity detection. This model uses pre-trained word embeddings for word vector generation and a range of filters to extract local features and long-term dependencies in text. It incorporates a fully connected layer, a normalization layer, and an output layer for multilabel category prediction. The proposed hybrid model demonstrates superior classification accuracy in experimental trials. It was tested on a dataset divided into training and testing sets, enhanced by significant pre-processing. Structural modifications, including increasing dense units and filters, were evaluated. The final model, combining GRUs with a single CNN layer, achieved an accuracy of 0.9944 in classifying toxic comments. The study evidences the efficacy of a hybrid GRU and single-layer CNN model in online toxic comment classification. Results suggest that simpler model architectures, supplemented by extensive pre-processing, yield high accuracy and efficient training. The findings underscore the importance of further research to understand biases in trained classifiers and suggest exploring alternative methods for representing sequences and independent training of sparsely labeled classes in future\u00a0work.<\/jats:p>","DOI":"10.1515\/jisys-2024-0108","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T10:56:02Z","timestamp":1768906562000},"source":"Crossref","is-referenced-by-count":0,"title":["A novel hybrid BGRU-CNN approach for multilabel toxicity detection in online environments"],"prefix":"10.1515","volume":"35","author":[{"given":"Benoi","family":"Alex","sequence":"first","affiliation":[{"name":"MIT Art , Design and Technology University , Loni Kalbhor , Pune , Maharashtra , India"}]},{"given":"Dhanalekshmi Prasad","family":"Yedurkar","sequence":"additional","affiliation":[{"name":"MIT Art , Design and Technology University , Loni Kalbhor , Pune , Maharashtra , India"}]},{"given":"Fadi","family":"Al-Turjman","sequence":"additional","affiliation":[{"name":"Software and AI Engineering Departments, Research Center for AI and IoT, Faculty of AI and Informatics , Near East University , Nicosia , Mersin 10 , T\u00fcrkiye"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6578-6919","authenticated-orcid":false,"given":"Thompson","family":"Stephan","sequence":"additional","affiliation":[{"name":"Thumbay College of Management and AI in Healthcare , Gulf Medical University , Ajman , United Arab Emirates"}]},{"given":"Yasir","family":"Hamid","sequence":"additional","affiliation":[{"name":"Information System Engineering Technology, Abu Dhabi Polytechnic , Abu Dhabi , United Arab Emirates"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2821-5423","authenticated-orcid":false,"given":"Mohd Asif","family":"Shah","sequence":"additional","affiliation":[{"name":"Kardan University , Kabul , Afghanistan"},{"name":"Division of Research and Development , Lovely Professional University , Phagwara , Punjab , , India"},{"name":"University Centre for Research & Development , Chandigarh University , Gharuan , Mohali , Punjab , , India"}]}],"member":"374","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"key":"2026012010555885967_j_jisys-2024-0108_ref_001","unstructured":"Stats. (2020), World Internet users and 2020 population stats, https:\/\/www.internetworldstats.com\/stats.htm [Accessed: Nov. 6, 2022] [Online]."},{"key":"2026012010555885967_j_jisys-2024-0108_ref_002","unstructured":"M. Duggan, \u201cOnline harassment,\u201d in Pew Res. Center, Washington, DC, USA, Tech. Rep., 2014. [Online]."},{"key":"2026012010555885967_j_jisys-2024-0108_ref_003","doi-asserted-by":"crossref","unstructured":"P. Badjatiya \net al\n., \u201cDeep learning for hate speech detection in tweets,\u201d in Proc. 26th Int. Conf. World Wide Web Companion, Perth, Australia, 2017, pp. 759\u2013760.","DOI":"10.1145\/3041021.3054223"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_004","doi-asserted-by":"crossref","unstructured":"E. Wulczyn, N. Thain, and L. Dixon, \u201cEx machina: Personal attacks seen at scale,\u201d in Proc. 26th Int. Conf. World Wide Web Perth Australia, 2017, pp. 1391\u20131399.","DOI":"10.1145\/3038912.3052591"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_005","doi-asserted-by":"crossref","unstructured":"S. Agrawal and A. Awekar, \u201cDeep learning for detecting cyberbullying across multiple social media platforms,\u201d in Proc. Eur. Conf. Inf. Retr, Cham, Switzerland, Springer, 2018, pp.\u00a0141\u2013153.","DOI":"10.1007\/978-3-319-76941-7_11"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_006","doi-asserted-by":"crossref","unstructured":"M. Ibrahim, M. Torki, and N. El-Makky, \u201cImbalanced toxic comments classification using data augmentation and deep learning,\u201d in Proc. 17th IEEE Int. Conf. Mach. Learn. Appl. (ICMLA) Orlando, Florida, 2018, pp. 875\u2013878.","DOI":"10.1109\/ICMLA.2018.00141"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_007","doi-asserted-by":"crossref","unstructured":"S. R. Basha and J. Keziya Rani, \u201cA comparative approach of dimensionality reduction techniques in text classification,\u201d Eng., Technol. Appl. Sci. Res., vol. 9, no. 4, pp. 4974\u20134979, 2019. https:\/\/doi.org\/10.48084\/etasr.3146.","DOI":"10.48084\/etasr.3146"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_008","doi-asserted-by":"crossref","unstructured":"S. Alam and N. Yao, \u201cThe impact of preprocessing steps on the accuracy of machine learning algorithms in sentiment analysis,\u201d Comput. Math. Org. Theory, vol. 25, no. 3, pp. 319\u2013335, 2019. https:\/\/doi.org\/10.1007\/s10588-018-9266-8.","DOI":"10.1007\/s10588-018-9266-8"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_009","doi-asserted-by":"crossref","unstructured":"F. Rustam, M. Khalid, W. Aslam, V. Rupapara, A. Mehmood, and G. S. Choi, \u201cA performance comparison of supervised machine learning models for COVID-19 tweets sentiment analysis,\u201d PLoS One, vol. 16, no. 2, 2021, Art. no. e0245909.","DOI":"10.1371\/journal.pone.0245909"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_010","doi-asserted-by":"crossref","unstructured":"O. Boutkhoum, B. Omar, E. M. Abdelmajid, F. Rustam, A. Mehmood, and G. S. Choi, \u201cMinimizing the overlapping degree to improve class imbalanced learning under sparse feature selection: Application to fraud detection,\u201d IEEE Access, vol.\u00a09, pp.\u00a028101\u201328110, 2021, https:\/\/doi.org\/10.1109\/access.2021.3056285.","DOI":"10.1109\/ACCESS.2021.3056285"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_011","doi-asserted-by":"crossref","unstructured":"M. Umer, I. Ashraf, A. Mehmood, S. Kumari, S. Ullah, and G. Sang Choi, \u201cSentiment analysis of tweets using a unified convolutional neural network-long short-term memory network model,\u201d Comput. Intell., vol. 37, no. 1, pp. 409\u2013434, 2021. https:\/\/doi.org\/10.1111\/coin.12415.","DOI":"10.1111\/coin.12415"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_012","doi-asserted-by":"crossref","unstructured":"C. Nobata \net al\n., \u201cAbusive language detection in online user content,\u201d in Proc. 25th Int. Conf. World Wide Web. Republic and Canton of Geneva, Switzer Land: International World Wide Web Conferences Steering Committee, Montreal, Quebec, Canada, 2016, pp. 145\u2013153.","DOI":"10.1145\/2872427.2883062"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_013","doi-asserted-by":"crossref","unstructured":"Y. Chen \net al\n., \u201cDetecting offensive language in social media to protect adolescent online safety,\u201d in Privacy, Security, Risk and Trust (PASSAT), 2012 International Conference on and 2012 International Conference on Social Computing (SocialCom), Amsterdam, Netherlands, IEEE, 2012, pp. 71\u201380.","DOI":"10.1109\/SocialCom-PASSAT.2012.55"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_014","unstructured":"W. Warner and J. Hirschberg, \u201cDetecting hate speech on the world wide web,\u201d in Proceedings of the Second Workshop on Language in Social Media, Association for Computational Linguistics, 7 June 2012, Montreal, Canada, 2012, pp. 19\u201326."},{"key":"2026012010555885967_j_jisys-2024-0108_ref_015","unstructured":"F. Del Vigna, A. Cimino, F. Dell\u2019Orletta, M. Petrocchi, and M. Tesconi. \u201cHate me, hate me not: Hate speech detection on facebook,\u201d in Proceedings of the first Italian conference on cybersecurity (ITASEC17), 2017, pp. 86\u201395."},{"key":"2026012010555885967_j_jisys-2024-0108_ref_016","doi-asserted-by":"crossref","unstructured":"B. Nathan \net al\n., \u201cBig data in drug discovery,\u201d in Machine Learning and Systems Biology in Genomics and Health, Singapore, Springer, 2022, pp.\u00a017\u201348.","DOI":"10.1007\/978-981-16-5993-5_2"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_017","doi-asserted-by":"crossref","unstructured":"L. Dixon, J. Li, J. Sorensen, N. Thain, and L. Vasserman. \u201cMeasuring and mitigating unintended bias in text classification,\u201d in Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society, 2018, 67\u201373.","DOI":"10.1145\/3278721.3278729"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_018","doi-asserted-by":"crossref","unstructured":"H. Fan et al., \u201cSocial media toxicity classification using deep learning: Real-world application UK brexit,\u201d Electronics, vol.\u00a010, no. 11, p.\u00a01332, 2021, https:\/\/doi.org\/10.3390\/electronics10111332.","DOI":"10.3390\/electronics10111332"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_019","doi-asserted-by":"crossref","unstructured":"K. B. Nelatoori and H. B. Kommanti, \u201cMulti-task learning for toxic comment classification and rationale extraction,\u201d J.\u00a0Intell. Inf. Syst., vol.\u00a060, no. 2, pp.\u00a0495\u2013519, 2023, https:\/\/doi.org\/10.1007\/s10844-022-00726-4.","DOI":"10.1007\/s10844-022-00726-4"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_020","unstructured":"Y. Parikh and J. Fiaidhi, \u201cRegional language toxic comment classification,\u201d Authorea Preprints, 2023. Available at: https:\/\/d197for5662m48.cloudfront.net\/documents\/publicationstatus\/168183\/preprint_pdf\/0fbeaa8d9fe3ac9e8e0ee1b81bd9ec2d.pdf."},{"key":"2026012010555885967_j_jisys-2024-0108_ref_021","doi-asserted-by":"crossref","unstructured":"J. Sarker, A. Kamal Turzo, M. Dong, and A. Bosu, \u201cAutomated identification of toxic code reviews using toxicr,\u201d ACM Trans. Software Eng. Methodol., vol.\u00a032, no. 5, pp.\u00a01\u201332, 2023, https:\/\/doi.org\/10.1145\/3583562.","DOI":"10.1145\/3583562"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_022","unstructured":"K. Poojitha, A. Sai Charish, M. Reddy, and S. Ayyasamy, \u201cClassification of social media toxic comments using Machine learning models,\u201d arXiv preprint arXiv:2304.06934, 2023."},{"key":"2026012010555885967_j_jisys-2024-0108_ref_023","doi-asserted-by":"crossref","unstructured":"S. Park and K. Lee, \u201cTackling faceless killers: Toxic comment detection to maintain a healthy internet environment,\u201d Comput., Mater. Continua, vol.\u00a076, no. 1, pp.\u00a0813\u2013826, 2023, https:\/\/doi.org\/10.32604\/cmc.2023.035313.","DOI":"10.32604\/cmc.2023.035313"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_024","doi-asserted-by":"crossref","unstructured":"H. B. Pramod and M. Goutham, \u201cDeep convolutional network based approach for detection of liver cancer and predictive analytics on cloud,\u201d in Machine Learning for Healthcare, Chapman and Hall\/CRC, 2020, pp.\u00a095\u2013114.","DOI":"10.1201\/9780429330131-8"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_025","doi-asserted-by":"crossref","unstructured":"A. Aggarwal and A. Tiwari, \u201cMulti label toxic comment classification using machine learning algorithms,\u201d Int. J.\u00a0Recent Technol. Eng. (lJRTE), vol.\u00a010, no. I, pp.\u00a02021\u2013161, 2021, https:\/\/doi.org\/10.35940\/ijrte.a5814.0510121.","DOI":"10.35940\/ijrte.A5814.0510121"},{"key":"2026012010555885967_j_jisys-2024-0108_ref_026","unstructured":"kaish114, \u201cToxic comments exploratory data analysis,\u201d GitHub, 2020."},{"key":"2026012010555885967_j_jisys-2024-0108_ref_027","doi-asserted-by":"crossref","unstructured":"M. T. Luong, H. Pham, and C. D. Manning, \u201cBilingual word representations with monolingual quality in mind,\u201d in Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing Denver, Colorado, USA, 2015, pp. 151\u2013159.","DOI":"10.3115\/v1\/W15-1521"}],"container-title":["Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2024-0108\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2024-0108\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T10:56:06Z","timestamp":1768906566000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2024-0108\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,20]]},"published-print":{"date-parts":[[2026,1,23]]}},"alternative-id":["10.1515\/jisys-2024-0108"],"URL":"https:\/\/doi.org\/10.1515\/jisys-2024-0108","relation":{},"ISSN":["2191-026X"],"issn-type":[{"value":"2191-026X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"article-number":"20240108"}}