{
 "id": "jeanlee/kmhas_korean_hate_speech",
 "owner": "jeanlee",
 "name": "kmhas_korean_hate_speech",
 "downloads": 335,
 "likes": 24,
 "last_modified": "2022-11-28T16:26:56.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{lee-etal-2022-k,\n    title = \"K-{MH}a{S}: A Multi-label Hate Speech Detection Dataset in {K}orean Online News Comment\",\n    author = \"Lee, Jean  and\n      Lim, Taejun  and\n      Lee, Heejun  and\n      Jo, Bogeun  and\n      Kim, Yangsok  and\n      Yoon, Heegeun  and\n      Han, Soyeon Caren\",\n    booktitle = \"Proceedings of the 29th International Conference on Computational Linguistics\",\n    month = oct,\n    year = \"2022\",\n    address = \"Gyeongju, Republic of Korea\",\n    publisher = \"International Committee on Computational Linguistics\",\n    url = \"https://aclanthology.org/2022.coling-1.311\",\n    pages = \"3530--3538\",\n    abstract = \"Online hate speech detection has become an important issue due to the growth of online content, but resources in languages other than English are extremely limited. We introduce K-MHaS, a new multi-label dataset for hate speech detection that effectively handles Korean language patterns. The dataset consists of 109k utterances from news comments and provides a multi-label classification using 1 to 4 labels, and handles subjectivity and intersectionality. We evaluate strong baselines on K-MHaS. KR-BERT with a sub-character tokenizer outperforms others, recognizing decomposed characters in each hate speech class.\",\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "c657d15baf277c48d467f0625f7d33c50d4352ef",
 "stated_evidence": "https://huggingface.co/datasets/jeanlee/kmhas_korean_hate_speech/blob/c657d15baf277c48d467f0625f7d33c50d4352ef/README.md",
 "file_evidence": "https://huggingface.co/datasets/jeanlee/kmhas_korean_hate_speech/tree/c657d15baf277c48d467f0625f7d33c50d4352ef",
 "card_nc": false
}