{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T01:57:46Z","timestamp":1781315866845,"version":"3.54.1"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100005801","name":"Facebook","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005801","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s10579-023-09696-7","type":"journal-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T12:02:16Z","timestamp":1700136136000},"page":"757-837","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A multilingual, multimodal dataset of aggression and bias: the ComMA dataset"],"prefix":"10.1007","volume":"58","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5151-2546","authenticated-orcid":false,"given":"Ritesh","family":"Kumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shyam","family":"Ratan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siddharth","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enakshi","family":"Nandi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laishram Niranjana","family":"Devi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akash","family":"Bhagat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yogesh","family":"Dawer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bornini","family":"Lahiri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akanksha","family":"Bansal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,16]]},"reference":[{"key":"9696_CR1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511618284","volume-title":"Language and social relations","author":"A Agha","year":"2007","unstructured":"Agha, A. (2007). Language and social relations. Cambridge: Cambridge University Press. https:\/\/doi.org\/10.1017\/CBO9780511618284"},{"key":"9696_CR2","doi-asserted-by":"publisher","unstructured":"Akhtar, S., Basile, V., & Patti, V. (2019). A new measure of polarization in the annotation of hate speech. In Proceedings of the international conference of the Italian association for artificial intelligence, pp. 588\u2013603. https:\/\/doi.org\/10.1007\/978-3-030-35166-3_41","DOI":"10.1007\/978-3-030-35166-3_41"},{"key":"9696_CR3","doi-asserted-by":"publisher","first-page":"83","DOI":"10.5121\/csit.2019.90208","volume":"2019","author":"A Al-Hassan","year":"2019","unstructured":"Al-Hassan, A., & Al-Dossari, H. (2019). Detection of hate speech in social networks: A survey on multilingual corpus. Computer Science and Information Technology, 2019, 83\u2013100. https:\/\/doi.org\/10.5121\/csit.2019.90208","journal-title":"Computer Science and Information Technology"},{"key":"9696_CR4","doi-asserted-by":"publisher","unstructured":"Albadi, N., Kurdi, M., & Mishra, S. (2018). Are they our brothers? analysis and detection of religious hate speech in the arabic twittersphere. In Proceedings of the 2018 IEEE\/ACM international conference on advances in social networks analysis and mining, pp. 69\u201376. https:\/\/doi.org\/10.1109\/ASONAM.2018.8508247","DOI":"10.1109\/ASONAM.2018.8508247"},{"key":"9696_CR5","doi-asserted-by":"publisher","unstructured":"Alfina, I., Mulia, R., Fanany, M.I., et\u00a0al. (2017). Hate speech detection in the indonesian language: A dataset and preliminary study. In Proceedings of 2017 international conference on advanced computer science and information systems (ICACSIS), IEEE. https:\/\/doi.org\/10.1109\/ICACSIS.2017.8355039","DOI":"10.1109\/ICACSIS.2017.8355039"},{"key":"9696_CR6","unstructured":"Amjad, M., Zhila, A., Sidorov, G., et\u00a0al. (2021). Overview of abusive and threatening language detection in urdu at fire 2021. In Proceedings of the 12th forum for information retrieval evaluation (FIRE). Association for computing machinery, New York, USA, pp. 744\u2013762."},{"key":"9696_CR7","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/978-3-031-12638-3_12","volume-title":"Advances in computing and data sciences","author":"AA Aporna","year":"2022","unstructured":"Aporna, A. A., Azad, I., Amlan, N. S., et al. (2022). Classifying offensive speech of bangla text and analysis using explainable ai. In M. Singh, V. Tyagi, P. K. Gupta, et al. (Eds.), Advances in computing and data sciences (pp. 133\u2013144). Springer."},{"key":"9696_CR8","doi-asserted-by":"publisher","unstructured":"Banik, N., & Rahman, M.H.H. (2019). Toxicity detection on bengali social media comments using supervised models. In 2019 2nd international conference on Innovation in Engineering and Technology (ICIET), pp. 1\u20135. https:\/\/doi.org\/10.1109\/ICIET48527.2019.9290710","DOI":"10.1109\/ICIET48527.2019.9290710"},{"key":"9696_CR9","unstructured":"Bhattacharya, S., Singh, S., Kumar, R., et\u00a0al. (2020). Developing a multilingual annotated corpus of misogyny and aggression. In Proceedings of the second workshop on trolling, aggression and cyberbullying. European Language Resources Association (ELRA), Marseille, France, pp. 158\u2013168, https:\/\/aclanthology.org\/2020.trac-1.25"},{"key":"9696_CR10","doi-asserted-by":"publisher","unstructured":"Bohra, A., Vijay, D., Singh, V., et\u00a0al. (2018). A dataset of Hindi-English code-mixed social media text for hate speech detection. In Proceedings of the second workshop on computational modeling of people\u2019s opinions, personality, and emotions in social media. Association for Computational Linguistics, New Orleans, Louisiana, USA, pp. 36\u201341. https:\/\/doi.org\/10.18653\/v1\/W18-1105. https:\/\/aclanthology.org\/W18-1105","DOI":"10.18653\/v1\/W18-1105"},{"key":"9696_CR11","doi-asserted-by":"publisher","unstructured":"Chakraborty, P., & Seddiqui, M.H. (2019). Threat and abusive language detection on social media in bengali language. In 2019 1st international conference on Advances in Science, Engineering and Robotics Technology (ICASERT), pp. 1\u20136. https:\/\/doi.org\/10.1109\/ICASERT.2019.8934609","DOI":"10.1109\/ICASERT.2019.8934609"},{"key":"9696_CR12","doi-asserted-by":"publisher","unstructured":"Chen, Y., Zhou, Y., Zhu, S., et\u00a0al. (2012). Detecting offensive language in social media to protect adolescent online safety. In 2012 international conference on privacy, security, risk and trust and 2012 international confernece on social computing, pp. 71\u201380. https:\/\/doi.org\/10.1109\/SocialCom-PASSAT.2012.55","DOI":"10.1109\/SocialCom-PASSAT.2012.55"},{"key":"9696_CR13","doi-asserted-by":"publisher","unstructured":"Chung, Y.L., Kuzmenko, E., Tekiroglu, S.S., et\u00a0al. (2019). CONAN - COunter NArratives through nichesourcing: a multilingual dataset of responses to fight online hate speech. In Proceedings of the 57th annual meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, pp. 2819\u20132829. https:\/\/doi.org\/10.18653\/v1\/P19-1271. https:\/\/aclanthology.org\/P19-1271","DOI":"10.18653\/v1\/P19-1271"},{"key":"9696_CR14","doi-asserted-by":"crossref","unstructured":"Conneau, A., Khandelwal, K., Goyal, N., et\u00a0al. (2019). Unsupervised cross-lingual representation learning at scale. CoRR . arXiv:1911.02116","DOI":"10.18653\/v1\/2020.acl-main.747"},{"issue":"1","key":"9696_CR15","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1515\/jisys-2020-0060","volume":"30","author":"AK Das","year":"2021","unstructured":"Das, A. K., Asif, A. A., Paul, A., et al. (2021). Bangla hate speech detection on social media using attention-based recurrent neural network. Journal of Intelligent Systems, 30(1), 578\u2013591. https:\/\/doi.org\/10.1515\/jisys-2020-0060","journal-title":"Journal of Intelligent Systems"},{"key":"9696_CR16","doi-asserted-by":"publisher","unstructured":"David, A. B. (2015). Descriptive grammar of Bangla: DE GRUYTER. https:\/\/doi.org\/10.1515\/9781614512295. www.degruyter.com\/document\/doi\/10.1515\/9781614512295\/html","DOI":"10.1515\/9781614512295"},{"key":"9696_CR17","doi-asserted-by":"crossref","unstructured":"Davidson, T., Warmsley, D., Macy, M., et al, (2017). Automated hate speech detection and the problem of offensive language. In Proceedings of the eleventh international conference on web and social media, AAAI, pp. 512\u2013515.","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"9696_CR18","doi-asserted-by":"publisher","unstructured":"de Pelle, R., & Moreira, V.P. (2016). Offensive comments in the brazilian web: A dataset and baseline results. In Proceedings of the fifth Brazilian workshop on social network analysis and mining (BraSNAM 2016), p 510\u2013519. https:\/\/doi.org\/10.5753\/brasnam.2017.3260","DOI":"10.5753\/brasnam.2017.3260"},{"key":"9696_CR19","unstructured":"Del Vigna, F., Cimino, A., Dell\u2019Orletta, F., et\u00a0al. (2017). Hate me, hate me not: Hate speech detection on facebook. In Proceedings of the First Italian conference on cybersecurity (ITASEC17), CEUR.org, pp. 86\u201395."},{"key":"9696_CR20","unstructured":"Devlin, J., Chang, M., Lee, K., et\u00a0al. (2018). BERT: pre-training of deep bidirectional transformers for language understanding. CoRR arXiv:1810.04805"},{"key":"9696_CR21","doi-asserted-by":"publisher","unstructured":"D\u2019Orazio, V., Kenwick, M., Lane, M., et\u00a0al. (2016). Crowdsourcing the measurement of interstate conflict. PLoS ONE, 11(6), e0156,527. https:\/\/doi.org\/10.1371\/journal.pone.0156527","DOI":"10.1371\/journal.pone.0156527"},{"key":"9696_CR22","doi-asserted-by":"publisher","unstructured":"Eshan, S.C., & Hasan, M.S. (2017). An application of machine learning to detect abusive bengali text. In 2017 20th international conference of Computer and Information Technology (ICCIT), pp. 1\u20136. https:\/\/doi.org\/10.1109\/ICCITECHN.2017.8281787","DOI":"10.1109\/ICCITECHN.2017.8281787"},{"key":"9696_CR23","doi-asserted-by":"publisher","unstructured":"Fernquist, J., Lindholm, O., Kaati, L., et\u00a0al. (2019). A study on the feasibility to detect hate speech in swedish. In 2019 IEEE international conference on big data (Big Data), 2019, IEEE, pp. 4724\u20134729. https:\/\/doi.org\/10.1109\/BigData47090.2019.9005534","DOI":"10.1109\/BigData47090.2019.9005534"},{"key":"9696_CR24","doi-asserted-by":"publisher","unstructured":"Fortuna, P., Rocha da Silva, J., Soler-Company, J., et\u00a0al. (2019). A hierarchically-labeled Portuguese hate speech dataset. In Proceedings of the third workshop on abusive language online. Association for Computational Linguistics, Florence, Italy, pp. 94\u2013104. https:\/\/doi.org\/10.18653\/v1\/W19-3510. https:\/\/aclanthology.org\/W19-3510","DOI":"10.18653\/v1\/W19-3510"},{"key":"9696_CR25","doi-asserted-by":"publisher","unstructured":"Haddad, H., Mulki, H., & Oueslati, A. (2019). T-hsab: A tunisian hate speech and abusive dataset. In 7th international conference on Arabic language processing, pp. 251\u2013263. https:\/\/doi.org\/10.1007\/978-3-030-32959-4_18","DOI":"10.1007\/978-3-030-32959-4_18"},{"key":"9696_CR26","doi-asserted-by":"publisher","unstructured":"Hammer, H. (2017). Automatic detection of hateful comments in online discussion. In Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, pp. 164\u2013173. https:\/\/doi.org\/10.1007\/978-3-319-52569-3_15","DOI":"10.1007\/978-3-319-52569-3_15"},{"key":"9696_CR27","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3544583","author":"MG Hussain","year":"2019","unstructured":"Hussain, M. G., & Mahmud, T. A. (2019). A technique for perceiving abusive Bangla comments. Green University of Bangladesh Journal of Science and Engineering. https:\/\/doi.org\/10.5281\/zenodo.3544583","journal-title":"Green University of Bangladesh Journal of Science and Engineering"},{"key":"9696_CR28","doi-asserted-by":"publisher","unstructured":"Ishmam, A., & Sharmin, S. (2019). Hateful speech detection in public facebook pages for the bengali language. In 18th IEEE international conference on machine learning and applications, ICMLA 2019, Boca Raton, FL, USA, pp. 555\u2013560. https:\/\/doi.org\/10.1109\/ICMLA.2019.00104","DOI":"10.1109\/ICMLA.2019.00104"},{"key":"9696_CR29","doi-asserted-by":"publisher","unstructured":"Islam, T., Ahmed, N., & Latif, S. (2021). An evolutionary approach to comparative analysis of detecting bangla abusive text. Bulletin of Electrical Engineering and Informatics, 10, 2163\u20132169. https:\/\/doi.org\/10.11591\/eei.v10i4.3107","DOI":"10.11591\/eei.v10i4.3107"},{"key":"9696_CR30","doi-asserted-by":"publisher","unstructured":"Joshi, P., Santy, S., Budhiraja, A., et\u00a0al. (2020). The state and fate of linguistic diversity and inclusion in the NLP world. In Proceedings of the 58th annual meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, pp. 6282\u20136293. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.560https:\/\/aclanthology.org\/2020.acl-main.560","DOI":"10.18653\/v1\/2020.acl-main.560"},{"key":"9696_CR31","doi-asserted-by":"publisher","unstructured":"Jurgens, D., Hemphill, L., & Chandrasekharan, E. (2019). A just and comprehensive strategy for using NLP to address online abuse. In Proceedings of the 57th annual meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, pp. 3658\u20133666. https:\/\/doi.org\/10.18653\/v1\/P19-1357https:\/\/aclanthology.org\/P19-1357","DOI":"10.18653\/v1\/P19-1357"},{"key":"9696_CR32","unstructured":"Kaggle (2020). Jigsaw multilingual toxic comment classification. https:\/\/www.kaggle.com\/c\/jigsaw-multilingual-toxic-comment-classification\/discussion\/138198"},{"key":"9696_CR33","doi-asserted-by":"crossref","unstructured":"Kakwani, D., Kunchukuttan, A., Golla, S., et\u00a0al. (2020). IndicNLPSuite: monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages. In Findings of EMNLP","DOI":"10.18653\/v1\/2020.findings-emnlp.445"},{"key":"9696_CR34","doi-asserted-by":"publisher","unstructured":"Karim, M.R., Dey, S.K., Islam, T., et\u00a0al. (2021). Deephateexplainer: Explainable hate speech detection in under-resourced bengali language. In 2021 IEEE 8th international conference on Data Science and Advanced Analytics (DSAA), pp. 1\u201310. https:\/\/doi.org\/10.1109\/DSAA53316.2021.9564230","DOI":"10.1109\/DSAA53316.2021.9564230"},{"key":"9696_CR35","doi-asserted-by":"publisher","unstructured":"Karim, M.R., Raja Chakravarthi, B., McCrae, J.P., et\u00a0al. (2020). Classification benchmarks for under-resourced bengali language based on multichannel convolutional-lstm network. In 2020 IEEE 7th international conference on Data Science and Advanced Analytics (DSAA), pp. 390\u2013399. https:\/\/doi.org\/10.1109\/DSAA49011.2020.00053","DOI":"10.1109\/DSAA49011.2020.00053"},{"key":"9696_CR36","unstructured":"Khanuja, S., Bansal, D., Mehtani, S., et\u00a0al. (2021). Muril: Multilingual representations for Indian languages. arXiv:2103.10730"},{"key":"9696_CR37","doi-asserted-by":"publisher","DOI":"10.1007\/s41701-019-00065-w","author":"V Kolhatkar","year":"2020","unstructured":"Kolhatkar, V., Wu, H., Cavasso, L., et al. (2020). The sfu opinion and comments corpus: A corpus for the analysis of online news comments. Corpus Pragmatics. https:\/\/doi.org\/10.1007\/s41701-019-00065-w","journal-title":"Corpus Pragmatics"},{"key":"9696_CR38","doi-asserted-by":"publisher","unstructured":"Kumar, R., Lahiri, B., & Ojha, A. (2021). Aggressive and offensive language identification in Hindi, Bangla, and English: A comparative study. SN Computer Science. https:\/\/doi.org\/10.1007\/s42979-020-00414-6","DOI":"10.1007\/s42979-020-00414-6"},{"key":"9696_CR39","unstructured":"Kumar, R., Ojha, A.K., Malmasi, S., et\u00a0al. (2018a). Benchmarking aggression identification in social media. In Proceedings of the first workshop on trolling, aggression and cyberbullying (TRAC-2018). Association for Computational Linguistics, Santa Fe, New Mexico, USA, pp. 1\u201311. https:\/\/aclanthology.org\/W18-4401"},{"key":"9696_CR40","unstructured":"Kumar, R., Ojha, A.K., Malmasi, S., et\u00a0al. (2020). Evaluating aggression identification in social media. In Proceedings of the second workshop on trolling, aggression and cyberbullying. European Language Resources Association (ELRA), Marseille, France, pp. 1\u20135. https:\/\/aclanthology.org\/2020.trac-1.1"},{"key":"9696_CR41","unstructured":"Kumar, R., Ratan, S., Singh, S., et\u00a0al. (2022). The comma dataset v0.2: Annotating aggression and bias in multilingual social media discourse. In Proceedings of the language resources and evaluation conference. European Language Resources Association, Marseille, France, pp. 4149\u20134161. https:\/\/aclanthology.org\/2022.lrec-1.441"},{"key":"9696_CR42","unstructured":"Kumar, R., Reganti, A. N., Bhatia, A., et\u00a0al. (2018b). Aggression-annotated corpus of Hindi-English code-mixed data. In Proceedings of the eleventh international conference on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA), Miyazaki, Japan. https:\/\/aclanthology.org\/L18-1226"},{"key":"9696_CR43","doi-asserted-by":"publisher","unstructured":"Malmasi, S., & Zampieri, M. (2017). Detecting hate speech in social media. In Proceedings of the international conference Recent Advances in Natural Language Processing, RANLP 2017. INCOMA Ltd., Varna, Bulgaria, pp. 467\u2013472. https:\/\/doi.org\/10.26615\/978-954-452-049-6_062","DOI":"10.26615\/978-954-452-049-6_062"},{"key":"9696_CR44","doi-asserted-by":"crossref","unstructured":"Mandl, T., Modha, S., Shahi, G.K., et\u00a0al. (2020). Overview of the hasoc track at fire 2020: Hate speech and offensive content identification in indo-european languages. In Proceedings of the 11th forum for information retrieval evaluation (FIRE). Association for Computing Machinery, New York, USA, p 29\u201332.","DOI":"10.1145\/3368567.3368584"},{"key":"9696_CR45","doi-asserted-by":"crossref","unstructured":"Mandl, T., Modha, S., Shahi, G.K., et\u00a0al. (2021). Overview of the hasoc subtrack at fire 2021: Hatespeech and offensive content identification in english and indo-aryan languages. In Proceedings of the 12th forum for information retrieval evaluation (FIRE). Association for Computing Machinery, New York, USA, pp. 1\u201319.","DOI":"10.1145\/3503162.3503176"},{"key":"9696_CR46","doi-asserted-by":"publisher","unstructured":"Martins, R., Gomes, M., Almeida, J., et\u00a0al. (2018). Hate speech classification in social media using emotional analysis. In Proceedings of the 2018 Brazilian conference on intelligent systems, BRACIS 2018, pp. 61\u201366. https:\/\/doi.org\/10.1109\/BRACIS.2018.00019","DOI":"10.1109\/BRACIS.2018.00019"},{"key":"9696_CR47","doi-asserted-by":"publisher","unstructured":"Mathur, P., Shah, R., Sawhney, R., et\u00a0al. (2018). Detecting offensive tweets in Hindi-English code-switched language. In Proceedings of the Sixth international workshop on Natural Language Processing for Social Media. Association for Computational Linguistics, Melbourne, Australia, pp. 18\u201326. https:\/\/doi.org\/10.18653\/v1\/W18-3504https:\/\/aclanthology.org\/W18-3504","DOI":"10.18653\/v1\/W18-3504"},{"key":"9696_CR48","doi-asserted-by":"publisher","unstructured":"Mubarak, H., Darwish, K., Magdy, W. (2017). Abusive language detection on Arabic social media. In Proceedings of the First Workshop on Abusive Language Online. Association for Computational Linguistics, Vancouver, BC, Canada, pp. 52\u201356. https:\/\/doi.org\/10.18653\/v1\/W17-3008https:\/\/aclanthology.org\/W17-3008","DOI":"10.18653\/v1\/W17-3008"},{"key":"9696_CR49","doi-asserted-by":"publisher","unstructured":"Nascimento, G., Carvalho, F., Cunha, A., et\u00a0al. (2019). Hate speech detection using brazilian imageboards. In Proceedings of the 25th Brazillian symposium on multimedia and the web, WebMedia 2019, pp. 325\u2013328. https:\/\/doi.org\/10.1145\/3323503.3360619","DOI":"10.1145\/3323503.3360619"},{"key":"9696_CR50","doi-asserted-by":"publisher","unstructured":"Nobata, C., Tetreault, J., Thomas, A., et\u00a0al. (2016). Abusive language detection in online user content. In Proceedings of the 25th international conference on world wide web (WWW\u201916). International World Wide Web Conferences Steering Committee, pp. 145\u2013153. https:\/\/doi.org\/10.1145\/2872427.2883062","DOI":"10.1145\/2872427.2883062"},{"key":"9696_CR51","doi-asserted-by":"publisher","unstructured":"Ousidhoum, N., Lin, Z., Zhang, H., et\u00a0al. (2019). Multilingual and multi-aspect hate speech analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, pp. 4675\u20134684. https:\/\/doi.org\/10.18653\/v1\/D19-1474https:\/\/aclanthology.org\/D19-1474","DOI":"10.18653\/v1\/D19-1474"},{"key":"9696_CR52","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1007\/s10579-020-09502-8","volume":"55","author":"F Poletto","year":"2021","unstructured":"Poletto, F., Basile, V., Sanguinetti, M., et al. (2021). Resources and benchmark corpora for hate speech detection: a systematic review. Lang Resour Evaluation, 55, 477\u2013523. https:\/\/doi.org\/10.1007\/s10579-020-09502-8","journal-title":"Lang Resour Evaluation"},{"key":"9696_CR53","doi-asserted-by":"publisher","unstructured":"Ranasinghe, T., & Zampieri, M. (2021). An evaluation of multilingual offensive language identification methods for the languages of india. Information 12(8). https:\/\/doi.org\/10.3390\/info12080306. https:\/\/www.mdpi.com\/2078-2489\/12\/8\/306","DOI":"10.3390\/info12080306"},{"key":"9696_CR54","doi-asserted-by":"publisher","unstructured":"Ritu, S.S., Mondal, J., Mia, M.M., et\u00a0al. (2021). Bangla abusive language detection using machine learning on radio message gateway. In 2021 6th international conference on Communication and Electronics Systems (ICCES), pp. 1725\u20131729. https:\/\/doi.org\/10.1109\/ICCES51350.2021.9489131","DOI":"10.1109\/ICCES51350.2021.9489131"},{"key":"9696_CR55","unstructured":"Romim, N., Ahmed, M., Islam, M.S., et\u00a0al. (2021a). HS-BAN: A benchmark dataset of social media comments for hate speech detection in bangla. arXiv:2112.01902"},{"key":"9696_CR56","doi-asserted-by":"publisher","unstructured":"Romim, N., Ahmed, M., Islam, M.S., et\u00a0al. (2022). Bd-shs: A benchmark dataset for learning to detect online bangla hate speech in different social contexts. https:\/\/doi.org\/10.48550\/ARXIV.2206.00372. arXiv:2206.00372","DOI":"10.48550\/ARXIV.2206.00372"},{"key":"9696_CR57","doi-asserted-by":"crossref","unstructured":"Romim, N., Ahmed, M., Talukder, H., et\u00a0al. (2021b). Hate speech detection in the bengali language: A dataset and its baseline evaluation. In: Uddin, M.S., & Bansal, J.C. (eds) Proceedings of International Joint Conference on Advances in Computational Intelligence. Springer Singapore, Singapore, pp. 457\u2013468.","DOI":"10.1007\/978-981-16-0586-4_37"},{"key":"9696_CR58","doi-asserted-by":"publisher","unstructured":"Rosenthal, S., Atanasova, P., Karadzhov, G., et\u00a0al. (2021). Solid: A large-scale semi-supervised dataset for offensive language identification. pp. 915\u2013928. https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.80","DOI":"10.18653\/v1\/2021.findings-acl.80"},{"key":"9696_CR59","doi-asserted-by":"publisher","unstructured":"Ross, B., Rist, M., Carbonell, G., et\u00a0al. (2017). Measuring the reliability of hate speech annotations: The case of the european refugee crisis. In NLP4CMC III: 3rd workshop on natural language processing for computer-mediated communication. https:\/\/doi.org\/10.17185\/duepublico\/42132","DOI":"10.17185\/duepublico\/42132"},{"key":"9696_CR60","unstructured":"Sanguinetti, M., Poletto, F., Bosco, C., et\u00a0al. (2018). An Italian Twitter corpus of hate speech against immigrants. In Proceedings of the Eleventh international conference on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA), Miyazaki, Japan, p 2798\u20132895, https:\/\/aclanthology.org\/L18-1443"},{"key":"9696_CR61","unstructured":"Sanh, V., Debut, L., Chaumond, J., et\u00a0al. (2019). Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. ArXiv arXiv:1910.01108"},{"key":"9696_CR62","doi-asserted-by":"publisher","unstructured":"Sazzed, S. (2021a). Abusive content detection in transliterated Bengali-English social media corpus. In Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching. Association for Computational Linguistics, Online, pp. 125\u2013130. https:\/\/doi.org\/10.18653\/v1\/2021.calcs-1.16. https:\/\/aclanthology.org\/2021.calcs-1.16","DOI":"10.18653\/v1\/2021.calcs-1.16"},{"key":"9696_CR63","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.665","author":"S Sazzed","year":"2021","unstructured":"Sazzed, S. (2021). Identifying vulgarity in bengali social media textual content. PeerJ Comput Sci. https:\/\/doi.org\/10.7717\/peerj-cs.665","journal-title":"PeerJ Comput Sci"},{"key":"9696_CR64","doi-asserted-by":"publisher","unstructured":"Sch\u00e4fer, J., & Burtenshaw, B. (2019). Offence in dialogues: A corpus-based study. In Proceedings of the international conference on Recent Advances in Natural Language Processing (RANLP 2019) INCOMA Ltd., Varna, Bulgaria, pp. 1085\u20131093. https:\/\/doi.org\/10.26615\/978-954-452-056-4_125https:\/\/aclanthology.org\/R19-1125","DOI":"10.26615\/978-954-452-056-4_125"},{"key":"9696_CR65","unstructured":"Schluter, N., & Agi\u0107, \u017d. (2017). Empirically sampling Universal Dependencies. In Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies (UDW 2017). Association for Computational Linguistics, Gothenburg, Sweden, pp. 117\u2013122, https:\/\/aclanthology.org\/W17-0415."},{"key":"9696_CR66","doi-asserted-by":"publisher","unstructured":"Schmidt, A., & Wiegand, M. (2017). A survey on hate speech detection using natural language processing. In Proceedings of the Fifth international workshop on Natural Language Processing for Social Media. Association for Computational Linguistics, Valencia, Spain, pp. 1\u201310. https:\/\/doi.org\/10.18653\/v1\/W17-1101. https:\/\/aclanthology.org\/W17-1101","DOI":"10.18653\/v1\/W17-1101"},{"key":"9696_CR67","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1016\/j.neucom.2021.12.022","volume":"490","author":"O Sharif","year":"2022","unstructured":"Sharif, O., & Hoque, M. M. (2022). Tackling cyber-aggression: Identification and fine-grained categorization of aggressive texts on social media using weighted ensemble of transformers. Neurocomputing, 490, 462\u2013481. https:\/\/doi.org\/10.1016\/j.neucom.2021.12.022","journal-title":"Neurocomputing"},{"key":"9696_CR68","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/978-3-030-73696-5_2","volume-title":"Combating Online Hostile Posts in Regional Languages during Emergency Situation","author":"O Sharif","year":"2021","unstructured":"Sharif, O., Hoque, M. M., et al. (2021). Identification and classification of textual aggression in social media: Resource creation and evaluation. In T. Chakraborty, K. Shu, & H. R. Bernard (Eds.), Combating Online Hostile Posts in Regional Languages during Emergency Situation (pp. 9\u201320). Cham: Springer International Publishing."},{"key":"9696_CR69","doi-asserted-by":"crossref","unstructured":"Shmueli, B., Fell, J., Ray, S., et\u00a0al. (2021). Beyond fair pay: Ethical implications of NLP crowdsourcing. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, p 3758\u20133769, https:\/\/aclanthology.org\/2021.naacl-main.295","DOI":"10.18653\/v1\/2021.naacl-main.295"},{"key":"9696_CR70","doi-asserted-by":"publisher","unstructured":"Steinberger, J., Brychc\u00edn, T., Hercig, T., et\u00a0al. (2017). Cross-lingual flames detection in news discussions. In Proceedings of the international conference Recent Advances in Natural Language Processing, RANLP 2017. INCOMA Ltd., Varna, Bulgaria, pp. 694\u2013700. https:\/\/doi.org\/10.26615\/978-954-452-049-6_089","DOI":"10.26615\/978-954-452-049-6_089"},{"issue":"e0243","key":"9696_CR71","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1371\/journal.pone.0243300","volume":"15","author":"B Vidgen","year":"2020","unstructured":"Vidgen, B., & Derczynski, L. (2020). Directions in abusive language training data, a systematic review: Garbage in, garbage out. PLOS ONE, 15(e0243), 300. https:\/\/doi.org\/10.1371\/journal.pone.0243300","journal-title":"PLOS ONE"},{"key":"9696_CR72","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1080\/19331681.2019.1702607","volume":"17","author":"B Vidgen","year":"2020","unstructured":"Vidgen, B., & Yasseri, T. (2020). Detecting weak and strong islamophobic hate speech on social media. Journal of Information Technology & Politics, 17, 66\u201378. https:\/\/doi.org\/10.1080\/19331681.2019.1702607","journal-title":"Journal of Information Technology & Politics"},{"key":"9696_CR73","doi-asserted-by":"publisher","unstructured":"Wang, S., Liu, J., Ouyang, X., et\u00a0al. (2020). Galileo at SemEval-2020 task 12: Multi-lingual learning for offensive language identification using pre-trained language models. In Proceedings of the Fourteenth Workshop on Semantic Evaluation. International Committee for Computational Linguistics, Barcelona (online), pp. 1448\u20131455. https:\/\/doi.org\/10.18653\/v1\/2020.semeval-1.189. https:\/\/aclanthology.org\/2020.semeval-1.189","DOI":"10.18653\/v1\/2020.semeval-1.189"},{"key":"9696_CR74","doi-asserted-by":"publisher","unstructured":"Waseem, Z. (2016). Are you a racist or am i seeing things? annotator influence on hate speech detection on twitter. In Proceedings of the first workshop on NLP and computational social science. Association for Computational Linguistics (ACL), pp. 138\u2013142. https:\/\/doi.org\/10.18653\/v1\/W16-5618","DOI":"10.18653\/v1\/W16-5618"},{"key":"9696_CR75","doi-asserted-by":"publisher","unstructured":"Waseem, Z., Davidson, T., Warmsley, D., et\u00a0al. (2017). Understanding abuse: A typology of abusive language detection subtasks. In Proceedings of the First Workshop on Abusive Language Online. Association for Computational Linguistics, Vancouver, BC, Canada, pp. 78\u201384. https:\/\/doi.org\/10.18653\/v1\/W17-3012https:\/\/aclanthology.org\/W17-3012","DOI":"10.18653\/v1\/W17-3012"},{"key":"9696_CR76","doi-asserted-by":"publisher","unstructured":"Waseem, Z., & Hovy, D. (2016). Hateful symbols or hateful people? predictive features for hate speech detection on Twitter. In Proceedings of the NAACL Student Research Workshop. Association for Computational Linguistics, San Diego, California, pp. 88\u201393. https:\/\/doi.org\/10.18653\/v1\/N16-2013. https:\/\/aclanthology.org\/N16-2013","DOI":"10.18653\/v1\/N16-2013"},{"key":"9696_CR77","doi-asserted-by":"publisher","unstructured":"Weingartner, S., & Stahel, L. (2019). Online aggression from a sociological perspective: An integrative view on determinants and possible countermeasures. In Proceedings of the third workshop on abusive language online. Association for Computational Linguistics, Florence, Italy, pp. 181\u2013187. https:\/\/doi.org\/10.18653\/v1\/W19-3520https:\/\/aclanthology.org\/W19-3520","DOI":"10.18653\/v1\/W19-3520"},{"key":"9696_CR78","doi-asserted-by":"publisher","unstructured":"Zampieri, M., Malmasi, S., Nakov, P., et\u00a0al. (2019a). Predicting the type and target of offensive posts in social media. 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). Association for Computational Linguistics, Minneapolis, Minnesota, pp. 1415\u20131420. https:\/\/doi.org\/10.18653\/v1\/N19-1144https:\/\/aclanthology.org\/N19-1144","DOI":"10.18653\/v1\/N19-1144"},{"key":"9696_CR79","doi-asserted-by":"publisher","unstructured":"Zampieri, M., Malmasi, S., Nakov, P., et\u00a0al. (2019b). SemEval-2019 task 6: Identifying and categorizing offensive language in social media (OffensEval). In Proceedings of the 13th international workshop on semantic evaluation. Association for Computational Linguistics, Minneapolis, Minnesota, USA, pp. 75\u201386. https:\/\/doi.org\/10.18653\/v1\/S19-2010https:\/\/aclanthology.org\/S19-2010","DOI":"10.18653\/v1\/S19-2010"},{"key":"9696_CR80","doi-asserted-by":"publisher","unstructured":"Zampieri, M., Nakov, P., Rosenthal, S., et\u00a0al. (2020). SemEval-2020 task 12: Multilingual offensive language identification in social media (OffensEval 2020). In Proceedings of the fourteenth workshop on semantic evaluation. International Committee for Computational Linguistics, Barcelona (online), pp. 1425\u20131447. https:\/\/doi.org\/10.18653\/v1\/2020.semeval-1.188https:\/\/aclanthology.org\/2020.semeval-1.188","DOI":"10.18653\/v1\/2020.semeval-1.188"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-023-09696-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10579-023-09696-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-023-09696-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T18:34:58Z","timestamp":1716921298000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10579-023-09696-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,16]]},"references-count":80,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["9696"],"URL":"https:\/\/doi.org\/10.1007\/s10579-023-09696-7","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,16]]},"assertion":[{"value":"20 September 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}