{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:24:41Z","timestamp":1771467881881,"version":"3.50.1"},"reference-count":60,"publisher":"Association for Computing Machinery (ACM)","issue":"11","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:p>In the modern digital world, social media has become essential for interpersonal interaction by promoting the interchange of ideas and points of view. But there are difficulties in this digital environment, especially concerning rude behavior and offensive remarks. To address both problems at once, the research focuses on sentiment analysis and abusive comment detection in social media interactions. The dataset contains Hate Speech and Offensive Content Identification (HASOC) data from 2019 to 2021 to identify hate speech in Hindi on various social media platforms. To categorize comments into abusive and non-abusive groups, several BERT models, including mBERT, DistilBERT, RoBERTa, HateBERT, and IndicBERT, have been utilized. Additionally, a comprehensive sentiment analysis of the derogatory comments has been performed. The research presents a stacked ensemble framework for binary (abusive and non-abusive) and multiclass (hate, offensive, and profane) classification that integrates predictions from mBERT, HateBERT, and IndicBERT models. Further, the study provides an integrated approach for providing abusive comment detection and sentiment analysis using a multi-output model. The proposed ensemble model achieves 94% accuracy in binary classification, with precision, recall, and F1 scores all approaching 94%. Multiclass ensemble models yield an accuracy of 93% and associated precision, recall, and F1 scores of 91%, 92%, and 92%, respectively. A comparative analysis using several state-of-the-art techniques has been generated to verify the efficacy of the suggested methodology.<\/jats:p>","DOI":"10.1145\/3766889","type":"journal-article","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:41:11Z","timestamp":1757590871000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Multi-Output BERT Framework for Abusive Comment Detection and Sentiment Analysis on Low-Resource Language"],"prefix":"10.1145","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7198-7950","authenticated-orcid":false,"given":"Mansi","family":"Yagnik","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Bharati Vidyapeeth's College of Engineering New Delhi","place":["New Delhi, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3261-7472","authenticated-orcid":false,"given":"Mehreen","family":"Hashmi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Bharati Vidyapeeth's College of Engineering New Delhi","place":["New Delhi, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6690-8500","authenticated-orcid":false,"given":"Deepika","family":"Kumar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Bharati Vidyapeeth's College of Engineering New Delhi","place":["New Delhi, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7676-8549","authenticated-orcid":false,"given":"Khushi","family":"Jain","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Bharati Vidyapeeth's College of Engineering New Delhi","place":["New Delhi, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9302-6707","authenticated-orcid":false,"given":"Ekagrah","family":"Grover","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Bharati Vidyapeeth's College of Engineering New Delhi","place":["New Delhi, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6091-1880","authenticated-orcid":false,"given":"Jude D","family":"Hemanth","sequence":"additional","affiliation":[{"name":"Department of Electronics & Communication Engineering, Karunya Institute of Technology and Sciences","place":["Coimbatore, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/SocialCom-PASSAT.2012.55"},{"issue":"5","key":"e_1_3_1_3_2","doi-asserted-by":"crossref","first-page":"103450","DOI":"10.1016\/j.ipm.2023.103450","article-title":"User-aware multilingual abusive content detection in social media","volume":"60","author":"Rehman M. Z. U.","year":"2023","unstructured":"M. Z. U. Rehman, S. Mehta, K. Singh, K. Kaushik, and N. Kumar. 2023. User-aware multilingual abusive content detection in social media. Information Processing and Management 60, 5 (2023), 103450.","journal-title":"Information Processing and Management"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC.2019.8819734"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2019.00008"},{"key":"e_1_3_1_6_2","unstructured":"G. I. Sigurbergsson and L. Derczynski. 2019. Offensive language and hate speech detection for Danish. arXiv: 1908.04531. Retrieved from https:\/\/arxiv.org\/abs\/1908.04531"},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/978-3-030-23943-5_16","volume-title":"Proceedings of the International Conference for Emerging Technologies in Computing","author":"Noor F.","year":"2019","unstructured":"F. Noor, M. Bakhtyar, and J. Baber. 2019. Sentiment analysis in e-commerce using svm on roman urdu text. In Proceedings of the International Conference for Emerging Technologies in Computing. Springer International Publishing. 213\u2013222."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0221152"},{"key":"e_1_3_1_9_2","volume-title":"Proceedings of the 2019 IEEE 4th International Conference on Computer and Communication Systems","author":"Das A. K.","year":"2019","unstructured":"A. K. Das, A. Ashrafi, and M. Ahmmad. 2019. Joint cognition of both human and machine for predicting criminal punishment in judicial system. In Proceedings of the 2019 IEEE 4th International Conference on Computer and Communication Systems. IEEE. 360\u201340."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102087"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3506"},{"issue":"6","key":"e_1_3_1_12_2","first-page":"1","article-title":"Social media use and its connection to mental health: A systematic review","volume":"12","author":"Karim F.","year":"2020","unstructured":"F. Karim, A. A. Oyewande, L. F. Abdalla, R. C. Ehsanullah, and S. Khan. 2020. Social media use and its connection to mental health: A systematic review. Cureus 12, 6 (2020), 1\u20136.","journal-title":"Cureus"},{"key":"e_1_3_1_13_2","unstructured":"https:\/\/firstsiteguide.com\/cyberbullying-stats\/"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2022.06.020"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207652"},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","first-page":"34","DOI":"10.18653\/v1\/2020.alw-1.5","volume-title":"Proceedings of the 4th Workshop on Online Abuse and Harms","author":"Koufakou A.","year":"2020","unstructured":"A. Koufakou, E. W. Pamungkas, V. Basile, and V. Patti. 2020. HurtBERT: Incorporating lexical features with BERT for the detection of abusive language. In Proceedings of the 4th Workshop on Online Abuse and Harms. Association for Computational Linguistics. 34\u201343."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42001-023-00224-9"},{"key":"e_1_3_1_18_2","first-page":"1","volume-title":"Proceedings of the 2020 International Conference for Emerging Technology","author":"Aind A. T.","year":"2020","unstructured":"A. T. Aind, A. Ramnaney, and D. Sethia. 2020. Q-bully: A reinforcement learning based cyberbullying detection framework. In Proceedings of the 2020 International Conference for Emerging Technology. IEEE. 1\u20136."},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.3390\/app122010342"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575860"},{"key":"e_1_3_1_21_2","first-page":"1","article-title":"Abusive language detection from social media comments using conventional machine learning and deep learning approaches","author":"Akhter M. P.","year":"2021","unstructured":"M. P. Akhter, Z. Jiangbin, I. R. Naqvi, M. AbdelMajeed, and T. Zia. 2021. Abusive language detection from social media comments using conventional machine learning and deep learning approaches. Multimedia Systems 28, 6 (2021), 1\u201316.","journal-title":"Multimedia Systems"},{"key":"e_1_3_1_22_2","doi-asserted-by":"crossref","unstructured":"A. Khan A. Ahmed S. Jan M. Bilal and M. F. Zuhairi. 2024. Abusive Language Detection in Urdu Text: Leveraging Deep Learning and Attention Mechanism. IEEE Access 12 (2024).","DOI":"10.1109\/ACCESS.2024.3370232"},{"key":"e_1_3_1_23_2","unstructured":"E. Shoukat R. Irfan I. Basharat M. A. Tahir and S. Shaukat. 2025. Attention based Bidirectional GRU hybrid model for inappropriate content detection in Urdu language. arXiv:2501.09722. Retrieved from https:\/\/arxiv.org\/abs\/2501.09722"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASERT.2019.8934609"},{"key":"e_1_3_1_25_2","first-page":"1","volume-title":"Proceedings of the 2019 7th International Conference on Smart Computing and Communications","author":"Emon E. A.","year":"2019","unstructured":"E. A. Emon, S. Rahman, J. Banarjee, A. K. Das, and T. Mittra. 2019. A deep learning approach to detect abusive bengali text. In Proceedings of the 2019 7th International Conference on Smart Computing and Communications IEEE, pp. 1\u20135."},{"key":"e_1_3_1_26_2","first-page":"457","volume-title":"Proceedings of the International Joint Conference on Advances in Computational Intelligence","author":"Romim N.","year":"2021","unstructured":"N. Romim, M. Ahmed, H. Talukder, and M. Saiful Islam. 2021. Hate speech detection in the bengali language: A dataset and its baseline evaluation. In Proceedings of the International Joint Conference on Advances in Computational Intelligence. Springer Singapore. 457\u2013468."},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dajour.2022.100073"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3029154"},{"key":"e_1_3_1_29_2","first-page":"113","volume-title":"Proceedings of the 1st Workshop on Trolling, Aggression and Cyberbullying","author":"Ora\u0161an C.","year":"2018","unstructured":"C. Ora\u0161an. 2018. Aggressive language identification using word embeddings and sentiment features. In Proceedings of the 1st Workshop on Trolling, Aggression and Cyberbullying. 113\u2013119."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3002176"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCS48705.2020.9074208"},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/978-981-19-7982-8_26","volume-title":"Mobile Radio Communications and 5G Networks: Proceedings of the 3rd MRCN 2022","author":"William P.","year":"2023","unstructured":"P. William, A. Shrivastava, P. S. Chauhan, M. Raja, S. B. Ojha, and K. Kumar. 2023. Natural Language processing implementation for sentiment analysis on tweets. In Mobile Radio Communications and 5G Networks: Proceedings of the 3rd MRCN 2022. Singapore: Springer Nature Singapore. 317\u2013327."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22114157"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC.2019.8743331"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909919"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/SMART46866.2019.9117512"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3027350"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2963702"},{"issue":"3","key":"e_1_3_1_39_2","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1080\/0952813X.2022.2093405","article-title":"A deep learning modified neural network (DLMNN) based proficient sentiment analysis technique on Twitter data","volume":"36","author":"Paulraj D.","year":"2024","unstructured":"D. Paulraj, P. Ezhumalai, and M. Prakash. 2024. A deep learning modified neural network (DLMNN) based proficient sentiment analysis technique on Twitter data. Journal of Experimental and Theoretical Artificial Intelligence 36, 3 (2024), 415\u2013434.","journal-title":"Journal of Experimental and Theoretical Artificial Intelligence"},{"key":"e_1_3_1_40_2","first-page":"940","volume-title":"Proceedings of the 23rd Conference on Computational Natural Language Learning","author":"Swamy S. D.","year":"2019","unstructured":"S. D. Swamy, A. Jamatia, and B. Gamb\u00e4ck. 2019. Studying generalisability across abusive language detection datasets. In Proceedings of the 23rd Conference on Computational Natural Language Learning. 940\u2013950."},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3441501.3441517"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503162.3503176"},{"key":"e_1_3_1_43_2","doi-asserted-by":"crossref","unstructured":"M. A. Shah M. J. Iqbal N. Noreen and I. Ahmed. 2023. An automated text document classification framework using BERT. Int. J. Adv. Comput. Sci. Appl 14 3 (2023) 279\u2013285.","DOI":"10.14569\/IJACSA.2023.0140332"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcce.2022.03.003"},{"key":"e_1_3_1_45_2","unstructured":"J. Devlin M. W. Chang K. Lee and K. Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Volume 1 (Long and Short Papers). 4171\u20134186."},{"key":"e_1_3_1_46_2","doi-asserted-by":"crossref","unstructured":"E. C. Garrido-Merchan R. Gozalo-Brizuela and S. Gonzalez-Carvajal. 2023. Comparing BERT against traditional machine learning models in text classification. Journal of Computational and Cognitive Engineering 2 4 (2023) 352\u2013356.","DOI":"10.47852\/bonviewJCCE3202838"},{"key":"e_1_3_1_47_2","first-page":"770","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He Kaiming","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770\u2013778."},{"key":"e_1_3_1_48_2","unstructured":"Jimmy Lei Ba Jamie Ryan Kiros and Geoffrey E Hinton. Layer normalization. arXiv:1607.06450. Retrieved from https:\/\/arxiv.org\/abs\/1607.06450"},{"issue":"3","key":"e_1_3_1_49_2","doi-asserted-by":"crossref","first-page":"3079","DOI":"10.32604\/cmc.2021.017371","article-title":"Development of social media analytics system for emergency event detection and crisis management","volume":"68","author":"Khatoon S.","year":"2021","unstructured":"S. Khatoon, M. A. Alshamari, A. Asif, M. M. Hasan, S. Abdou, K. M. Elsayed, and M. Rashwan. 2021. Development of social media analytics system for emergency event detection and crisis management. Computers, Materials and Continua 68, 3 (2021), 3079\u20133100.","journal-title":"Computers, Materials and Continua"},{"key":"e_1_3_1_50_2","doi-asserted-by":"crossref","unstructured":"T. Pires E. Schlinger and D. Garrette. 2019. How multilingual is multilingual BERT?. arXiv: 1906.01502. Retrieved from https:\/\/arxiv.org\/abs\/1906.01502","DOI":"10.18653\/v1\/P19-1493"},{"key":"e_1_3_1_51_2","doi-asserted-by":"crossref","unstructured":"T. Pires E. Schlinger and D. Garrette. 2019. How multilingual is multilingual BERT? arXiv preprint arXiv:1906.01502.","DOI":"10.18653\/v1\/P19-1493"},{"key":"e_1_3_1_52_2","first-page":"4948","volume-title":"Findings of the Association for Computational Linguistics","author":"Kakwani D.","year":"2020","unstructured":"D. Kakwani, A. Kunchukuttan, S. Golla, N. C. Gokul, A. Bhattacharyya, M. M. Khapra, and P. Kumar. 2020. IndicNLPSuite: Monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages. In Findings of the Association for Computational Linguistics. 4948\u20134961."},{"key":"e_1_3_1_53_2","unstructured":"A. Vaswani N. Shazeer N. Parmar J. Uszkoreit L. Jones A. N. Gomez and I. Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems. 30."},{"key":"e_1_3_1_54_2","doi-asserted-by":"crossref","unstructured":"T. Caselli V. Basile J. Mitrovi\u0107 and M. Granitzer. 2020. Hatebert: Retraining bert for abusive language detection in english. arXiv:2010.12472. Retrieved from https:\/\/arxiv.org\/abs\/2010.12472","DOI":"10.18653\/v1\/2021.woah-1.3"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2015.04.004"},{"key":"e_1_3_1_56_2","first-page":"4025","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Sun S.","year":"2020","unstructured":"S. Sun, A. Krishnan, Y. Belinkov, H. Duan, L. Pang, and J. Peng. 2020. IndicBERT: Pre-training a BERT stack for Indian languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics. 4025\u20134032."},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.5555\/648054.743935"},{"key":"e_1_3_1_58_2","unstructured":"A. Velankar H. Patil A. Gore S. Salunke and R. Joshi. 2021. Hate and offensive speech detection in hindi and marathi. arXiv:2110.12200. Retrieved from https:\/\/arxiv.org\/abs\/2110.12200"},{"key":"e_1_3_1_59_2","first-page":"338","volume-title":"Proceedings of the FIRE (Working Notes)","author":"Jadhav I.","year":"2021","unstructured":"I. Jadhav, A. Kanade, V. Waghmare, and D. Chaudhari. 2021. Hate and Offensive Speech Detection in Hindi Twitter Corpus. In Proceedings of the FIRE (Working Notes). 338\u2013348."},{"key":"e_1_3_1_60_2","unstructured":"M. Bhatia T. S. Bhotia A. Agarwal P. Ramesh S. Gupta K. Shridhar ... and A. Dash. 2021. One to rule them all: Towards joint indic language hate speech detection. arXiv:2109.13711. Retrieved from https:\/\/arxiv.org\/abs\/2109.13711"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503162.3503176"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3766889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T14:01:35Z","timestamp":1761314495000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3766889"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"references-count":60,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3766889"],"URL":"https:\/\/doi.org\/10.1145\/3766889","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,24]]},"assertion":[{"value":"2024-05-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}