{
 "id": "mteb/IndonesianIdClickbaitClassification",
 "owner": "mteb",
 "name": "IndonesianIdClickbaitClassification",
 "downloads": 1359,
 "likes": 0,
 "last_modified": "2025-05-06T12:32:54.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@article{WILLIAM2020106231,\n  abstract = {News analysis is a popular task in Natural Language Processing (NLP). In particular, the problem of clickbait in news analysis has gained attention in recent years [1, 2]. However, the majority of the tasks has been focused on English news, in which there is already a rich representative resource. For other languages, such as Indonesian, there is still a lack of resource for clickbait tasks. Therefore, we introduce the CLICK-ID dataset of Indonesian news headlines extracted from 12 Indonesian online news publishers. It is comprised of 15,000 annotated headlines with clickbait and non-clickbait labels. Using the CLICK-ID dataset, we then developed an Indonesian clickbait classification model achieving favourable performance. We believe that this corpus will be useful for replicable experiments in clickbait detection or other experiments in NLP areas.},\n  author = {Andika William and Yunita Sari},\n  doi = {https://doi.org/10.1016/j.dib.2020.106231},\n  issn = {2352-3409},\n  journal = {Data in Brief},\n  keywords = {Indonesian, Natural Language Processing, News articles, Clickbait, Text-classification},\n  pages = {106231},\n  title = {CLICK-ID: A novel dataset for Indonesian clickbait headlines},\n  url = {http://www.sciencedirect.com/science/article/pii/S2352340920311252},\n  volume = {32},\n  year = {2020},\n}\n\n\n@article{enevoldsen2025mmtebmassivemultilingualtext,\n  title={MMTEB: Massive Multilingual Text Embedding Benchmark},\n  author={Kenne",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "fa22e2fe229619ae18cd236e23f538abf828f171",
 "stated_evidence": "https://huggingface.co/datasets/mteb/IndonesianIdClickbaitClassification/blob/fa22e2fe229619ae18cd236e23f538abf828f171/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/IndonesianIdClickbaitClassification/tree/fa22e2fe229619ae18cd236e23f538abf828f171",
 "card_nc": false
}