{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T11:04:08Z","timestamp":1751281448500,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031790379"},{"type":"electronic","value":"9783031790386"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-79038-6_2","type":"book-chapter","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T06:18:21Z","timestamp":1738217901000},"page":"18-30","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Transformer-Based Tabular Approach to\u00a0Detect Toxic Comments"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5466-6607","authenticated-orcid":false,"given":"Ghivvago","family":"Damas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4209-9013","authenticated-orcid":false,"given":"Rafael","family":"Torres Anchi\u00eata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1558-3830","authenticated-orcid":false,"given":"Raimundo","family":"Santos Moura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3391-8443","authenticated-orcid":false,"given":"Vinicius","family":"Ponte Machado","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,31]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Almeida, T.G., Souza, B.\u00c0., Nakamura, F.G., Nakamura, E.F.: Detecting hate, offensive, and regular speech in short comments. In: Proceedings of the 23rd Brazillian Symposium on Multimedia and the Web (2017)","DOI":"10.1145\/3126858.3131576"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Assis, G., Amorim, A., Carvalho, J., de\u00a0Oliveira, D., Vianna, D., Paes, A.: Exploring Portuguese hate speech detection in low-resource settings: Lightly tuning encoder models or in-context learning of large models? In: Proceedings of the 16th International Conference on Computational Processing of Portuguese, ACL (2024)","DOI":"10.52591\/lxai202406212"},{"key":"2_CR3","unstructured":"Bertaglia, T.F.C., Nunes, M.d.G.V.: Exploring word embeddings for unsupervised textual user-generated content normalization. In: Proceedings of the 2nd Workshop on Noisy User-Generated Text (2016)"},{"key":"2_CR4","unstructured":"Bispo, T.D.: Arquitetura LSTM para classifica\u00e7\u00e3o de discursos de \u00f3dio cross-lingual Ingl\u00eas-PtBR. Master\u2019s thesis, Universidade Federal do Sergipe (2018)"},{"key":"2_CR5","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33 (2020)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Burnap, P., Williams, M.L.: Us and them: identifying cyber hate on twitter across multiple protected characteristics. EPJ Data Sci. 5 (2016)","DOI":"10.1140\/epjds\/s13688-016-0072-6"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., Liu, Z.: BGE M3-embedding: multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation (2023)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhou, Y., Zhu, S., Xu, H.: Detecting offensive language in social media to protect adolescent online safety. In: 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Conference on Social Computing. IEEE, Amsterdam (2012)","DOI":"10.1109\/SocialCom-PASSAT.2012.55"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Chopra, A., Sharma, D.K., Jha, A., Ghosh, U.: A framework for online hate speech detection on code-mixed Hindi-English text and Hindi text in Devanagari. ACM Trans. Asian Low-Resource Lang. Inf. Process. 22(5) (2023)","DOI":"10.1145\/3568673"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"De\u00a0Pelle, R.P., Moreira, V.P.: Offensive comments in the Brazilian web: a dataset and baseline results. In: Anais do VI Brazilian Workshop on Social Network Analysis and Mining, SBC (2017)","DOI":"10.5753\/brasnam.2017.3260"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Fortuna, P., Rocha\u00a0da Silva, J., Soler-Company, J., Wanner, L., Nunes, S.: A hierarchically-labeled Portuguese hate speech dataset. In: Proceedings of the Third Workshop on Abusive Language Online, ACL (2019)","DOI":"10.18653\/v1\/W19-3510"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Fortuna, P., Soler-Company, J., Wanner, L.: How well do hate speech, toxicity, abusive and offensive language classification models generalize across datasets? Inf. Process. Manag. 58(3) (2021)","DOI":"10.1016\/j.ipm.2021.102524"},{"key":"2_CR13","unstructured":"Gorishniy, Y., Rubachev, I., Khrulkov, V., Babenko, A.: Revisiting deep learning models for tabular data. Adv. Neural Inf. Process. Syst. 34 (2021)"},{"key":"2_CR14","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: Deberta: decoding-enhanced bert with disentangled attention. In: International Conference on Learning Representations (2021)"},{"key":"2_CR15","unstructured":"Hu, W., et al.: Pytorch frame: a modular framework for multi-modal tabular learning. arXiv preprint arXiv:2404.00776 (2024)"},{"key":"2_CR16","unstructured":"Khanuja, S., et al.: Muril: multilingual representations for Indian languages. arXiv preprint arXiv:2103.10730 (2021)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Leite, J.A., Silva, D., Bontcheva, K., Scarton, C.: Toxic language detection in social media for Brazilian Portuguese: new dataset and multilingual analysis. In: Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, ACL (2020)","DOI":"10.18653\/v1\/2020.aacl-main.91"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Malmasi, S., Zampieri, M.: Challenges in discriminating profanity from hate speech. J. Exp. Theor. Artif. Intell. 30(2) (2018)","DOI":"10.1080\/0952813X.2017.1409284"},{"key":"2_CR19","unstructured":"Mandal, A., Roy, G., Barman, A., Dutta, I., Naskar, S.K.: Attentive fusion: a transformer-based approach to multimodal hate speech detection. arXiv preprint arXiv:2401.10653 (2024)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: MTEB: massive text embedding benchmark. In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, ACL, Dubrovnik (2023)","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Nascimento, F.R., Cavalcanti, G.D., Da\u00a0Costa-Abreu, M.: Unintended bias evaluation: An analysis of hate speech detection and gender bias mitigation on social media using ensemble learning. Exp. Syst. Appl. 201 (2022)","DOI":"10.1016\/j.eswa.2022.117032"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Nobata, C., Tetreault, J., Thomas, A., Mehdad, Y., Chang, Y.: Abusive language detection in online user content. In: Proceedings of the 25th International Conference on World Wide Web, International World Wide Web Conferences Steering Committee, Montr\u00e9al (2016)","DOI":"10.1145\/2872427.2883062"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Ocampo, N.B., Sviridova, E., Cabrio, E., Villata, S.: An in-depth analysis of implicit and subtle hate speech messages. In: Vlachos, A., Augenstein, I. (eds.) Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 1997\u20132013. Association for Computational Linguistics, Dubrovnik (2023)","DOI":"10.18653\/v1\/2023.eacl-main.147"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Oliveira, A., Cecote, T., Silva, P., Gertrudes, J., Freitas, V., Luz, E.: How good is chatgpt for detecting hate speech in portuguese? In: Anais do XIV Simp\u00f3sio Brasileiro de Tecnologia da Informa\u00e7\u00e3o e da Linguagem Humana, SBC, Belo Horizonte\/MG (2023)","DOI":"10.5753\/stil.2023.233943"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Pelle, R., Alc\u00e2ntara, C., Moreira, V.P.: A classifier ensemble for offensive text detection. In: Proceedings of the 24th Brazilian Symposium on Multimedia and the Web (2018)","DOI":"10.1145\/3243082.3243111"},{"key":"2_CR26","unstructured":"Pires, R., Abonizio, H., Almeida, T.S., Nogueira, R.: Sabi\u00e1: Portuguese large language models. In: Intelligent Systems. Springer, Cham (2023). ISBN 978-3-031-45392-2"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Rawat, A., Kumar, S., Samant, S.S.: Hate speech detection in social media: techniques, recent trends, and future challenges. Wiley Interdiscip. Rev.: Comput. Statist. 16(2) (2024)","DOI":"10.1002\/wics.1648"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. 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), pp. 3982\u20133992. Association for Computational Linguistics, Hong Kong (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"da\u00a0Rocha\u00a0Junqueira, J., Junior, C.L., Silva, F.L.V., C\u00f4rrea, U.B., de\u00a0Freitas, L.A.: Albertina in action: an investigation of its abilities in aspect extraction, hate speech detection, irony detection, and question-answering. In: Anais do XIV Simp\u00f3sio Brasileiro de Tecnologia da Informa\u00e7\u00e3o e da Linguagem Humana, SBC (2023)","DOI":"10.5753\/stil.2023.234159"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Rodrigues, J.A., et al.: Advancing neural encoding of Portuguese with transformer albertina pt-*. In: Progress in Artificial Intelligence: 22nd EPIA Conference on Artificial Intelligence, EPIA 2023, Faial Island, 5\u20138 September 2023, Proceedings, Part I, pp. 441\u2013453. Springer, Berlin (2023). ISBN 978-3-031-49007-1","DOI":"10.1007\/978-3-031-49008-8_35"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez, S.E., Allende-Cid, H., Allende, H.: Detecting hate speech in cross-lingual and multi-lingual settings using language agnostic representations. In: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications: 25th Iberoamerican Congress, CIARP 2021. Springer (2021)","DOI":"10.1007\/978-3-030-93420-0_8"},{"key":"2_CR32","unstructured":"Saraiva, G.D., Anchi\u00eata, R., Neto, F.A.R., Moura, R.: A semi-supervised approach to detect toxic comments. In: Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), INCOMA Ltd., Held Online (2021)"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Silva, S., Serapiao, A.: Detec\u00e7\u00e3o de discurso de \u00f3dio em portugu\u00eas usando cnn combinada a vetores de palavras. In: Proceedings of KDMILE 2018, Symposium on Knowledge Discovery, Mining and Learning, S\u00e3o Paulo (2018)","DOI":"10.5753\/kdmile.2018.27378"},{"key":"2_CR34","unstructured":"da\u00a0Silva\u00a0Oliveira, A., de\u00a0Carvalho\u00a0Cecote, T., Alvarenga, J.P.R., de\u00a0Souza\u00a0Freitas, V.L., da\u00a0Silva\u00a0Luz, E.J.: Toxic speech detection in Portuguese: a comparative study of large language models. In: Proceedings of the 16th International Conference on Computational Processing of Portuguese, ACL (2024)"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Souza, F., Nogueira, R., Lotufo, R.: BERTimbau: pretrained BERT models for Brazilian Portuguese. In: 9th Brazilian Conference on Intelligent Systems, BRACIS, Rio Grande do Sul, 20\u201323 October (to appear) (2020)","DOI":"10.1007\/978-3-030-61377-8_28"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"\u00dcst\u00fcn, A., et\u00a0al.: AYA model: an instruction finetuned open-access multilingual language model. arXiv preprint arXiv:2402.07827 (2024)","DOI":"10.18653\/v1\/2024.acl-long.845"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Utku, A., Can, U., Aslan, S.: Detection of hateful twitter users with graph convolutional network model. Earth Sci. Inf. 16(1) (2023)","DOI":"10.1007\/s12145-023-00940-w"},{"key":"2_CR38","unstructured":"Vargas, F., Carvalho, I., Rodrigues\u00a0de G\u00f3es, F., Pardo, T., Benevenuto, F.: HateBR: a large expert annotated corpus of Brazilian Instagram comments for offensive language and hate speech detection. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, European Language Resources Association (2022)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Walther, J.B.: Social media and online hate. Curr. Opin. Psychol. 45 (2022)","DOI":"10.1016\/j.copsyc.2021.12.010"},{"key":"2_CR40","unstructured":"Wang, L., Yang, N., Huang, X., Yang, L., Majumder, R., Wei, F.: Multilingual e5 text embeddings: a technical report. arXiv preprint arXiv:2402.05672 (2024)"},{"key":"2_CR41","unstructured":"Wang, X., Koneru, S., Venkit, P.N., Frischmann, B., Rajtmajer, S.: The unappreciated role of intent in algorithmic moderation of social media content. arXiv preprint arXiv:2405.11030 (2024)"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Waseem, Z., Hovy, D.: Hateful symbols or hateful people? Predictive features for hate speech detection on Twitter. In: Proceedings of the NAACL Student Research Workshop (2016)","DOI":"10.18653\/v1\/N16-2013"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Yin, W., Zubiaga, A.: Towards generalisable hate speech detection: a review on obstacles and solutions. PeerJ Comput. Sci. 7 (2021)","DOI":"10.7717\/peerj-cs.598"},{"key":"2_CR44","unstructured":"Younus, A., Qureshi, M.A.: A framework for sexism detection on social media via byt5 and tabnet (2022)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-79038-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T06:18:39Z","timestamp":1738217919000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-79038-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031790379","9783031790386"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-79038-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"31 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bel\u00e9m do Par\u00e1","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}