{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T11:14:37Z","timestamp":1792062877821,"version":"4.4.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001538","name":"Victoria University of Wellington","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001538","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2022,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Hate speech detection mostly involves the use of text data. This data, usually sourced from various social media platforms, have been known to be plagued with numerous issues that result in a reduction of its quality and hence, the quality of the trained models. Some of these issues are the lack of diversity and the diminutive class of interest in the dataset which results in overfitted models that do not generalize well on other or newly collected data. The different ways of handling these issues include augmenting the data with diverse samples, engineering non-redundant features or designing robust classification models. In this study, the focus is on the data augmentation aspect. Data augmentation is a popular method for improving the quality of existing datasets by generating synthetic samples that mimic the distribution of the original samples. There is a lack of extensive studies on how hate speech texts respond to varying textual data augmentation techniques and methods. Specifically, we provide further insight into the token replacement method of textual data augmentation by performing empirical studies that investigate which embedding method(s) is a robust source of synonym for replacement process, what effective method(s) can be used to select words to be replaced, and how to confirm if the label within each class is preserved. Our proposed methods, validated on two commonly used hate speech datasets affected by a known lack of diversity and diminutive class of interest issues, significantly improve classification performance and provides insights into token replacement methods.<\/jats:p>","DOI":"10.1007\/s11280-022-01025-2","type":"journal-article","created":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T10:02:56Z","timestamp":1646128976000},"page":"1129-1150","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Token replacement-based data augmentation methods for hate speech detection"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1641-6767","authenticated-orcid":false,"given":"Kosisochukwu Judith","family":"Madukwe","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoying","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,3,1]]},"reference":[{"key":"1025_CR1","doi-asserted-by":"publisher","unstructured":"Alorainy, W., Burnap, P., Liu, H., Javed, A., Williams, M.L.: Suspended accounts: A source of tweets with disgust and anger emotions for augmenting hate speech data sample. In: 2018 International Conference on Machine Learning and Cybernetics (ICMLC), vol. 2, pp. 581\u2013586 (2018). https:\/\/doi.org\/10.1109\/ICMLC.2018.8527001","DOI":"10.1109\/ICMLC.2018.8527001"},{"key":"1025_CR2","unstructured":"Bodria, F., Panisson, A., Perotti, A., Piaggesi, S.: Explainability methods for natural language processing: applications to sentiment analysis. In: SEBD (2020)"},{"key":"1025_CR3","doi-asserted-by":"publisher","unstructured":"Cao, R., Lee, R.K.W.: HateGAN: Adversarial generative-based data augmentation for hate speech detection. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 6327\u20136338. International Committee on Computational Linguistics, Barcelona, Spain (Online) (2020). https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.557","DOI":"10.18653\/v1\/2020.coling-main.557"},{"key":"1025_CR4","unstructured":"Coulombe, C.: Text data augmentation made simple by leveraging NLP cloud apis (2018). arxiv:1812.04718"},{"key":"1025_CR5","unstructured":"Datta, D., Kumar, S., Barnes, L., Fletcher, T.: Geometry matters: Exploring language examples at the decision boundary (2020). arxiv:2010.07212"},{"key":"1025_CR6","doi-asserted-by":"crossref","unstructured":"Davidson, T., Warmsley, D., Macy, M., Weber, I.: Automated hate speech detection and the problem of offensive language. In: Proceedings of the 11th International AAAI Conference on Web and Social Media, ICWSM \u201917, pp. 512\u2013515 (2017)","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"1025_CR7","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: 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, pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"1025_CR8","unstructured":"Elmadany, A., Zhang, C., Abdul-Mageed, M., Hashemi, A.: Leveraging affective bidirectional transformers for offensive language detection. In: Proceedings of the 4th Workshop on Open-source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pp. 102\u2013108. European Language Resource Association, Marseille, France (2020). https:\/\/www.aclweb.org\/anthology\/2020.osact-1.17"},{"key":"1025_CR9","doi-asserted-by":"publisher","unstructured":"Fadaee, M., Bisazza, A., Monz, C.: Data augmentation for low-resource neural machine translation. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 567\u2013573. Association for Computational Linguistics, Vancouver, Canada (2017). https:\/\/doi.org\/10.18653\/v1\/P17-2090","DOI":"10.18653\/v1\/P17-2090"},{"key":"1025_CR10","unstructured":"Founta, A.M., Djouvas, C., Chatzakou, D., Leontiadis, I., Blackburn, J., Stringhini, G., Vakali, A., Sirivianos, M., Kourtellis, N.: Large scale crowdsourcing and characterization of twitter abusive behavior. In: Proceedings of the Twelfth International AAAI Conference on Web and Social Media (ICWSM 2018) (2018). arxiv:1802.00393"},{"key":"1025_CR11","doi-asserted-by":"publisher","unstructured":"Jain, S., Wallace, B.C.: Attention is not Explanation. 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), pp. 3543\u20133556. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1357","DOI":"10.18653\/v1\/N19-1357"},{"key":"1025_CR12","doi-asserted-by":"crossref","unstructured":"Juuti, M., Gr\u00f6ndahl, T., Flanagan, A., Asokan, N.: A little goes a long way: Improving toxic language classification despite data scarcity. In: Findings of the Association for Computational Linguistics: EMNLP (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.269"},{"key":"1025_CR13","doi-asserted-by":"publisher","unstructured":"Kebriaei, E., Karimi, S., Sabri, N., Shakery, A.: Emad at SemEval-2019 task 6: Offensive language identification using traditional machine learning and deep learning approaches. In: Proceedings of the 13th International Workshop on Semantic Evaluation, pp. 600\u2013603. Association for Computational Linguistics, Minneapolis, Minnesota, USA (2019). https:\/\/doi.org\/10.18653\/v1\/S19-2107","DOI":"10.18653\/v1\/S19-2107"},{"key":"1025_CR14","doi-asserted-by":"publisher","unstructured":"Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of ICNN\u201995 - International Conference on Neural Networks, vol. 4, pp. 1942\u20131948 vol.4 (1995). https:\/\/doi.org\/10.1109\/ICNN.1995.488968","DOI":"10.1109\/ICNN.1995.488968"},{"key":"1025_CR15","doi-asserted-by":"crossref","unstructured":"Komninos, A., Manandhar, S.: Dependency based embeddings for sentence classification tasks. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1490\u20131500. Association for Computational Linguistics, San Diego, California (2016). https:\/\/www.aclweb.org\/anthology\/N16-1175","DOI":"10.18653\/v1\/N16-1175"},{"key":"1025_CR16","doi-asserted-by":"crossref","unstructured":"Levy, O., Goldberg, Y.: Dependency-based word embeddings. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 302\u2013308. Association for Computational Linguistics, Baltimore, Maryland (2014). https:\/\/www.aclweb.org\/anthology\/P14-2050","DOI":"10.3115\/v1\/P14-2050"},{"key":"1025_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Cohn, T., Baldwin, T.: Robust training under linguistic adversity. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pp. 21\u201327. Association for Computational Linguistics, Valencia, Spain (2017). https:\/\/www.aclweb.org\/anthology\/E17-2004","DOI":"10.18653\/v1\/E17-2004"},{"key":"1025_CR18","unstructured":"Liu, R., Xu, G., Vosoughi, S.: Enhanced offensive language detection through data augmentation (2020)"},{"key":"1025_CR19","doi-asserted-by":"publisher","unstructured":"Madukwe, K., Gao, X., Xue, B.: In data we trust: A critical analysis of hate speech detection datasets. In: Proceedings of the Fourth Workshop on Online Abuse and Harms, pp. 150\u2013161. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.alw-1.18","DOI":"10.18653\/v1\/2020.alw-1.18"},{"key":"1025_CR20","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1007\/978-3-030-35288-2_28","volume-title":"AI 2019: Advances in Artificial Intelligence","author":"KJ Madukwe","year":"2019","unstructured":"Madukwe, K.J., Gao, X.: The thin line between hate and profanity. In: Liu, J., Bailey, J. (eds.) AI 2019: Advances in Artificial Intelligence, pp. 344\u2013356. Springer International Publishing, Cham (2019)"},{"key":"1025_CR21","doi-asserted-by":"publisher","unstructured":"Madukwe, K.J., Gao, X., Xue, B.: A ga-based approach to fine-tuning bert for hate speech detection. In: 2020 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 2821\u20132828 (2020). https:\/\/doi.org\/10.1109\/SSCI47803.2020.9308419","DOI":"10.1109\/SSCI47803.2020.9308419"},{"key":"1025_CR22","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013)"},{"key":"1025_CR23","doi-asserted-by":"crossref","unstructured":"Mozafari, M., Farahbakhsh, R., Crespi, N.: A bert-based transfer learning approach for hate speech detection in online social media (2019)","DOI":"10.1007\/978-3-030-36687-2_77"},{"key":"1025_CR24","doi-asserted-by":"crossref","unstructured":"Mrk\u0161i\u0107, N., \u00d3\u00a0S\u00e9aghdha, D., Thomson, B., Ga\u0161i\u0107, M., Rojas-Barahona, L.M., Su, P.H., Vandyke, D., Wen, T.H., Young, S.: Counter-fitting word vectors to linguistic constraints. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 142\u2013148. Association for Computational Linguistics, San Diego, California (2016). https:\/\/www.aclweb.org\/anthology\/N16-1018","DOI":"10.18653\/v1\/N16-1018"},{"key":"1025_CR25","doi-asserted-by":"publisher","unstructured":"Mudrakarta, P.K., Taly, A., Sundararajan, M., Dhamdhere, K.: Did the model understand the question? In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1896\u20131906. Association for Computational Linguistics, Melbourne, Australia (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1176","DOI":"10.18653\/v1\/P18-1176"},{"key":"1025_CR26","doi-asserted-by":"publisher","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543. Association for Computational Linguistics, Doha, Qatar (2014). https:\/\/doi.org\/10.3115\/v1\/D14-1162","DOI":"10.3115\/v1\/D14-1162"},{"key":"1025_CR27","doi-asserted-by":"publisher","unstructured":"Pitsilis, G., Ramampiaro, H., Langseth, H.: Effective hate-speech detection in twitter data using recurrent neural networks. Applied Intelligence 48, in press. (2018). https:\/\/doi.org\/10.1007\/s10489-018-1242-y","DOI":"10.1007\/s10489-018-1242-y"},{"key":"1025_CR28","doi-asserted-by":"crossref","unstructured":"Ramirez, J.M., Montalvo, A., Calvo, J.R.: A survey of the effects of data augmentation for automatic speech recognition systems. In: Nystr\u00f6m, I., Hern\u00e1ndez Heredia, Y., Mili\u00e1n\u00a0N\u00fa\u00f1ez V. (eds.) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, pp. 669\u2013678. Springer International Publishing, Cham (2019)","DOI":"10.1007\/978-3-030-33904-3_63"},{"key":"1025_CR29","doi-asserted-by":"publisher","unstructured":"Rathpisey, H., Adji, T.B.: Handling imbalance issue in hate speech classification using sampling-based methods. In: 2019 5th International Conference on Science in Information Technology (ICSITech), pp. 193\u2013198 (2019). https:\/\/doi.org\/10.1109\/ICSITech46713.2019.8987500","DOI":"10.1109\/ICSITech46713.2019.8987500"},{"key":"1025_CR30","doi-asserted-by":"crossref","unstructured":"Rizos, G., Hemker, K., Schuller, B.: Augment to prevent: short-text data augmentation in deep learning for hate-speech classification, p. 991-1000. Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3357384.3358040","DOI":"10.1145\/3357384.3358040"},{"key":"1025_CR31","doi-asserted-by":"publisher","unstructured":"\u015eahin, G.G., Steedman, M.: Data augmentation via dependency tree morphing for low-resource languages. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 5004\u20135009. Association for Computational Linguistics, Brussels, Belgium (2018). https:\/\/doi.org\/10.18653\/v1\/D18-1545","DOI":"10.18653\/v1\/D18-1545"},{"key":"1025_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., Khoshgoftaar, T.: A survey on image data augmentation for deep learning. Journal of Big Data 6, 1\u201348 (2019)","journal-title":"Journal of Big Data"},{"key":"1025_CR33","doi-asserted-by":"publisher","unstructured":"Simard, P.Y., LeCun, Y.A., Denker, J.S., Victorri, B.: Transformation Invariance in Pattern Recognition \u2014 Tangent Distance and Tangent Propagation, pp. 239\u2013274. Springer, Berlin (1998). https:\/\/doi.org\/10.1007\/3-540-49430-8_13","DOI":"10.1007\/3-540-49430-8_13"},{"key":"1025_CR34","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning - Volume 70, ICML\u201917, p. 3319-3328. JMLR.org (2017)"},{"key":"1025_CR35","doi-asserted-by":"crossref","unstructured":"Tang, X., Shen, X., Wang, Y., Yang, Y.: Categorizing offensive language in social networks: A chinese corpus, systems and an explanation tool. In: CNCL (2020)","DOI":"10.1007\/978-3-030-63031-7_22"},{"key":"1025_CR36","doi-asserted-by":"crossref","unstructured":"Tekiroglu, S.S., Chung, Y.L., Guerini, M.: Generating counter narratives against online hate speech: Data and strategies (2020)","DOI":"10.18653\/v1\/2020.acl-main.110"},{"issue":"3","key":"1025_CR37","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1109\/TEVC.2018.2869405","volume":"23","author":"B Tran","year":"2019","unstructured":"Tran, B., Xue, B., Zhang, M.: Variable-length particle swarm optimization for feature selection on high-dimensional classification. IEEE Transactions on Evolutionary Computation 23(3), 473\u2013487 (2019). https:\/\/doi.org\/10.1109\/TEVC.2018.2869405","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"1025_CR38","unstructured":"Vijayaraghavan, P., Larochelle, H., Roy, D.: Interpretable multi-modal hate speech detection (2021)"},{"key":"1025_CR39","doi-asserted-by":"publisher","unstructured":"Wang, W.Y., Yang, D.: That\u2019s so annoying!!!: A lexical and frame-semantic embedding based data augmentation approach to automatic categorization of annoying behaviors using #petpeeve tweets. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 2557\u20132563. Association for Computational Linguistics, Lisbon, Portugal (2015). https:\/\/doi.org\/10.18653\/v1\/D15-1306","DOI":"10.18653\/v1\/D15-1306"},{"key":"1025_CR40","doi-asserted-by":"crossref","unstructured":"Wei, J., Zou, K.: Eda: Easy data augmentation techniques for boosting performance on text classification tasks (2019)","DOI":"10.18653\/v1\/D19-1670"},{"key":"1025_CR41","doi-asserted-by":"crossref","unstructured":"Wright, A.P., Shaikh, O., Park, H., Epperson, W., Ahmed, M., Pinel, S., Chau, D.H., Yang, D.: RECAST: enabling user recourse and interpretability of toxicity detection models with interactive visualization (2021) arxiv:2102.04427","DOI":"10.1145\/3449280"},{"key":"1025_CR42","doi-asserted-by":"publisher","unstructured":"Wullach, T., Adler, A., Minkov, E.: Towards hate speech detection at large via deep generative modeling. IEEE Internet Computing pp. 1\u20131 (2020). https:\/\/doi.org\/10.1109\/MIC.2020.3033161","DOI":"10.1109\/MIC.2020.3033161"},{"key":"1025_CR43","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.asoc.2013.09.018","volume":"18","author":"B Xue","year":"2014","unstructured":"Xue, B., Zhang, M., Browne, W.N.: Particle swarm optimisation for feature selection in classification: Novel initialisation and updating mechanisms. Applied Soft Computing 18, 261\u2013276 (2014). https:\/\/doi.org\/10.1016\/j.asoc.2013.09.018","journal-title":"Applied Soft Computing"},{"key":"1025_CR44","unstructured":"Zarecki, J., Markovitch, S.: Textual membership queries (2018). arxiv:1805.04609"},{"key":"1025_CR45","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1, NIPS\u201915, p. 649-657. MIT Press, Cambridge, MA, USA (2015)"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-022-01025-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11280-022-01025-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-022-01025-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T04:15:34Z","timestamp":1674879334000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11280-022-01025-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,1]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["1025"],"URL":"https:\/\/doi.org\/10.1007\/s11280-022-01025-2","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"value":"1386-145X","type":"print"},{"value":"1573-1413","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,1]]},"assertion":[{"value":"21 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}