{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T16:51:59Z","timestamp":1777395119555,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819614820","type":"print"},{"value":"9789819614837","type":"electronic"}],"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\/978-981-96-1483-7_6","type":"book-chapter","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T19:37:44Z","timestamp":1740685064000},"page":"75-89","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Low-Resource Dataset Synthetic Generation for\u00a0Hate Speech Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2419-3570","authenticated-orcid":false,"given":"Adri\u00e1n","family":"Gir\u00f3n","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1998-8621","authenticated-orcid":false,"given":"Guillem","family":"Collell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2278-3611","authenticated-orcid":false,"given":"Fadi","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4127-5505","authenticated-orcid":false,"given":"Javier","family":"Huertas-Tato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5051-3475","authenticated-orcid":false,"given":"David","family":"Camacho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,28]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","unstructured":"Ilan, T., Vilenchik, D.: HARALD: augmenting hate speech data sets with real data. In: Findings of the Association for Computational Linguistics: EMNLP 2022. Goldberg, Y., Kozareva, Z., Zhang, Y., (eds.) Abu Dhabi, United Arab Emirates: Association for Computational Linguistics, pp.\u00a02241\u20132248 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.165. (Visited on 09\/23\/2024)","DOI":"10.18653\/v1\/2022.findings-emnlp.165"},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Belinkov, Y., Bisk, Y.: Synthetic and natural noise both break neural machine translation (2018). https:\/\/doi.org\/10.48550\/arXiv.1711.02173, arXiv:1711.02173 (2018) (Visited on 09\/18\/2024)","DOI":"10.48550\/arXiv.1711.02173"},{"key":"6_CR3","unstructured":"Mohamadi, S., et al.: ChatGPT in the age of generative AI and large language models: a concise survey. https:\/\/arxiv.org\/abs\/2307.04251v2 (2023). (Visited on 09\/19\/2024)"},{"key":"6_CR4","doi-asserted-by":"publisher","unstructured":"Jiang, A.Q., et al.: Mistral 7B. https:\/\/doi.org\/10.48550\/arXiv.2310.06825. arXiv: 2310.06825 (2023). (Visited on 09\/17\/2024)","DOI":"10.48550\/arXiv.2310.06825"},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning. https:\/\/doi.org\/10.48550\/arXiv.1712.04621. arXiv:1712.04621 (2017). (Visited on 09\/19\/2024)","DOI":"10.48550\/arXiv.1712.04621"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. https:\/\/doi.org\/10.48550\/arXiv.2006.11239. arXiv:2006.11239 (2020). (Visited on 09\/19\/2024)","DOI":"10.48550\/arXiv.2006.11239"},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Wei, J., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks. 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). Inui, K., et al. (eds.) Hong Kong, China: Association for Computational Linguistics, pp.\u00a06382\u20136388 (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1670. (Visited on 09\/18\/2024)","DOI":"10.18653\/v1\/D19-1670"},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Pavlick, E., et al.: PPDB 2.0: better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). Zong, C., Strube, M. (eds.) Beijing, China: Association for Computational Linguistics, pp.\u00a0425\u2013430 (2015). https:\/\/doi.org\/10.3115\/v1\/P15-2070. (Visited on 09\/18\/2024)","DOI":"10.3115\/v1\/P15-2070"},{"key":"6_CR9","doi-asserted-by":"publisher","unstructured":"Vaswani, A., et al.: Attention is all you need. https:\/\/doi.org\/10.48550\/arXiv.1706.03762. arXiv:1706.03762 (2023). (Visited on 11\/17\/2023)","DOI":"10.48550\/arXiv.1706.03762"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"Kobayashi, S.: Contextual augmentation: data augmentation by words with paradigmatic relations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). Walker, M., Ji, H., Stent, A. (eds.) New Orleans, Louisiana: Association for Computational Linguistics, pp.\u00a0452\u2013457 (2018). https:\/\/doi.org\/10.18653\/v1\/N18-2072. (Visited on 09\/12\/2024)","DOI":"10.18653\/v1\/N18-2072"},{"key":"6_CR11","unstructured":"Kumar, V., Choudhary, A., Cho, E.: Data Augmentation using pre-trained transformer models. arXiv: 2003.02245 (2021). (Visited on 09\/04\/2024)"},{"key":"6_CR12","doi-asserted-by":"publisher","unstructured":"Devlin, J., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. https:\/\/doi.org\/10.48550\/arXiv.1810.04805. arXiv: 1810.04805 (2019). (Visited on 11\/22\/2023)","DOI":"10.48550\/arXiv.1810.04805"},{"key":"6_CR13","doi-asserted-by":"publisher","unstructured":"Sennrich, R., Haddow, B., Birch, A.: improving neural machine translation models with monolingual data. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Erk, K., Smith, N.A., (eds.) Berlin, Germany: Association for Computational Linguistics, pp.\u00a086\u201396 (2016).. https:\/\/doi.org\/10.18653\/v1\/P16-1009. (Visited on 09\/12\/2024)","DOI":"10.18653\/v1\/P16-1009"},{"key":"6_CR14","unstructured":"Dai, H., et al.: AugGPT: leveraging ChatGPT for Text Data Augmentation. arXiv: 2302.13007 (2023). (Visited on 07\/18\/2024)"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Yoo, K.M., et al.: GPT3Mix: leveraging large-scale language models for text augmentation. arXiv: 2104.08826 (2021). (Visited on 09\/04\/2024)","DOI":"10.18653\/v1\/2021.findings-emnlp.192"},{"key":"6_CR16","unstructured":"Li, Z., et al.: Synthetic data generation with large language models for text classification: potential and limitations. arXiv: 2310.07849 (2023). (Visited on 09\/04\/2024)"},{"key":"6_CR17","unstructured":"Ye, J., et al.: ZeroGen: efficient zero-shot learning via dataset generation. arXiv: 2202.07922 (2022). (Visited on 07\/01\/2024)"},{"key":"6_CR18","unstructured":"Zelikman, E., et al.: STaR: bootstrapping reasoning with reasoning. arXiv: 2203.14465 (2022). (Visited on 07\/18\/2024)"},{"key":"6_CR19","unstructured":"Konen, K., et al.: Style vectors for steering generative large language model. arXiv: 2402.01618 (2024). (Visited on 06\/13\/2024)"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Khullar, A., et al.: Hate speech detection in limited data contexts using synthetic data generation. In: ACM J. Comput. Sustain. Soc. 2(1), 4:1\u20134:18 (2024). https:\/\/doi.org\/10.1145\/3625679. (Visited on 09\/12\/2024)","DOI":"10.1145\/3625679"},{"key":"6_CR21","unstructured":"Hartvigsen, T., et al.: ToxiGen: a large-scale machine-generated dataset for adversarial and implicit hate speech detection (2022). arXiv:2203.09509 (2022). (Visited on 09\/04\/2024)"},{"key":"6_CR22","doi-asserted-by":"publisher","unstructured":"Samory, M., et al.: Call me sexist, but : revisiting sexism detection using psychological scales and adversarial samples. In: Proceedings of the International AAAI Conference on Web and Social Media. vol.\u00a015. Association for the Advancement of Artificial Intelligence (AAAI), pp.\u00a0573\u2013584 (2021). https:\/\/doi.org\/10.1609\/icwsm.v15i1.18085. (Visited on 09\/17\/2024)","DOI":"10.1609\/icwsm.v15i1.18085"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Mollas, I., et al.: ETHOS: an online hate speech detection dataset. Complex Intell. Syst. 8(6), 4663\u20134678 (2022). ISSN: 2199-4536, 2198-6053. https:\/\/doi.org\/10.1007\/s40747-021-00608-2. arXiv: 2006.08328 (Visited on 09\/17\/2024)","DOI":"10.1007\/s40747-021-00608-2"},{"key":"6_CR24","doi-asserted-by":"publisher","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. https:\/\/doi.org\/10.48550\/arXiv.2203.02155. arXiv:2203.02155 (2022). (Visited on 09\/26\/2024)","DOI":"10.48550\/arXiv.2203.02155"},{"key":"6_CR25","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. https:\/\/arxiv.org\/abs\/1907.11692v1 (2019). (Visited on 09\/18\/2024)"},{"key":"6_CR26","unstructured":"He, P., et al.: DeBERTa: decoding-enhanced BERT with disentangled attention. arXiv: 2006.03654 (2021). (Visited on 05\/23\/2023)"},{"key":"6_CR27","unstructured":"Meister, C., et al.: Locally Typical Sampling. arXiv: 2202.00666 (2023). (Visited on 09\/27\/2024)"},{"key":"6_CR28","unstructured":"Keskar, N.S., et al.: CTRL: a conditional transformer language model for controllable generation. arXiv: 1909.05858 (2019). (Visited on 09\/27\/2024)"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems Engineering \u2013 WISE 2024 PhD Symposium, Demos and Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1483-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T19:37:50Z","timestamp":1740685070000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1483-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819614820","9789819614837"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1483-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"28 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WISE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Web Information Systems Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Doha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Qatar","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":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wise2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/wise2024-qatar.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}