{
 "id": "SEACrowd/id_abusive",
 "owner": "SEACrowd",
 "name": "id_abusive",
 "downloads": 132,
 "likes": 0,
 "last_modified": "2024-06-24T13:24:27.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-nc-nd-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "sentiment-analysis"
 ],
 "citation": "@article{IBROHIM2018222,\ntitle = {A Dataset and Preliminaries Study for Abusive Language Detection in Indonesian Social Media},\njournal = {Procedia Computer Science},\nvolume = {135},\npages = {222-229},\nyear = {2018},\nnote = {The 3rd International Conference on Computer Science and Computational Intelligence (ICCSCI 2018) : Empowering Smart Technology in Digital Era for a Better Life},\nissn = {1877-0509},\ndoi = {https://doi.org/10.1016/j.procs.2018.08.169},\nurl = {https://www.sciencedirect.com/science/article/pii/S1877050918314583},\nauthor = {Muhammad Okky Ibrohim and Indra Budi},\nkeywords = {abusive language, twitter, machine learning},\nabstract = {Abusive language is an expression (both oral or text) that contains abusive/dirty words or phrases both in the context of jokes, a vulgar sex conservation or to cursing someone. Nowadays many people on the internet (netizens) write and post an abusive language in the social media such as Facebook, Line, Twitter, etc. Detecting an abusive language in social media is a difficult problem to resolve because this problem can not be resolved just use word matching. This paper discusses a preliminaries study for abusive language detection in Indonesian social media and the challenge in developing a system for Indonesian abusive language detection, especially in social media. We also built reported an experiment for abusive language detection on Indonesian tweet using machine learning approach with a simple word n-gram and char n-gram feat",
 "signal": "restrictive",
 "reason": "The dataset card's licence name or licence section contains wording that suggests non-commercial, research-only or academic-only use restrictions.",
 "revision": "06c68c3c435249d71dd084bdc2b33be3dc95d71d",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/id_abusive/blob/06c68c3c435249d71dd084bdc2b33be3dc95d71d/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/id_abusive/blob/06c68c3c435249d71dd084bdc2b33be3dc95d71d/LICENSE",
 "card_nc": true
}