{
 "id": "mteb/InappropriatenessClassification",
 "owner": "mteb",
 "name": "InappropriatenessClassification",
 "downloads": 38,
 "likes": 0,
 "last_modified": "2025-05-06T12:23:08.000Z",
 "stated_licence": "cc-by-nc-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{babakov-etal-2021-detecting,\n  abstract = {Not all topics are equally {``}flammable{''} in terms of toxicity: a calm discussion of turtles or fishing less often fuels inappropriate toxic dialogues than a discussion of politics or sexual minorities. We define a set of sensitive topics that can yield inappropriate and toxic messages and describe the methodology of collecting and labelling a dataset for appropriateness. While toxicity in user-generated data is well-studied, we aim at defining a more fine-grained notion of inappropriateness. The core of inappropriateness is that it can harm the reputation of a speaker. This is different from toxicity in two respects: (i) inappropriateness is topic-related, and (ii) inappropriate message is not toxic but still unacceptable. We collect and release two datasets for Russian: a topic-labelled dataset and an appropriateness-labelled dataset. We also release pre-trained classification models trained on this data.},\n  address = {Kiyv, Ukraine},\n  author = {Babakov, Nikolay  and\nLogacheva, Varvara  and\nKozlova, Olga  and\nSemenov, Nikita  and\nPanchenko, Alexander},\n  booktitle = {Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing},\n  editor = {Babych, Bogdan  and\nKanishcheva, Olga  and\nNakov, Preslav  and\nPiskorski, Jakub  and\nPivovarova, Lidia  and\nStarko, Vasyl  and\nSteinberger, Josef  and\nYangarber, Roman  and\nMarci{\\'n}czuk, Micha{\\l}  and\nPollak, Senja  and\nP{\\v{r}}ib{\\'a}{\\v{n}}, Pavel  and\nRob",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "e4ca017792d50a0763ebc429f22784951fe19585",
 "stated_evidence": "https://huggingface.co/datasets/mteb/InappropriatenessClassification/blob/e4ca017792d50a0763ebc429f22784951fe19585/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/InappropriatenessClassification/tree/e4ca017792d50a0763ebc429f22784951fe19585",
 "card_nc": false
}