{
 "id": "SEACrowd/code_mixed_jv_id",
 "owner": "SEACrowd",
 "name": "code_mixed_jv_id",
 "downloads": 348,
 "likes": 0,
 "last_modified": "2024-06-24T13:23:04.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "sentiment-analysis",
  "machine-translation"
 ],
 "citation": "@article{Tho_2021,\n  doi = {10.1088/1742-6596/1869/1/012084},\n  url = {https://doi.org/10.1088/1742-6596/1869/1/012084},\n  year = 2021,\n  month = {apr},\n  publisher = {{IOP} Publishing},\n  volume = {1869},\n  number = {1},\n  pages = {012084},\n  author = {C Tho and Y Heryadi and L Lukas and A Wibowo},\n  title = {Code-mixed sentiment analysis of Indonesian language and Javanese language using Lexicon based approach},\n  journal = {Journal of Physics: Conference Series},\n  abstract = {Nowadays mixing one language with another language either in\n  spoken or written communication has become a common practice for bilingual\n  speakers in daily conversation as well as in social media. Lexicon based\n  approach is one of the approaches in extracting the sentiment analysis. This\n  study is aimed to compare two lexicon models which are SentiNetWord and VADER\n  in extracting the polarity of the code-mixed sentences in Indonesian language\n  and Javanese language. 3,963 tweets were gathered from two accounts that\n  provide code-mixed tweets. Pre-processing such as removing duplicates,\n  translating to English, filter special characters, transform lower case and\n  filter stop words were conducted on the tweets. Positive and negative word\n  score from lexicon model was then calculated using simple mathematic formula\n  in order to classify the polarity. By comparing with the manual labelling,\n  the result showed that SentiNetWord perform better than VADER in negative\n  sentiments. However, both ",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "dc88250f1d1df844f84b91dc07d140ac5099f39a",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/code_mixed_jv_id/blob/dc88250f1d1df844f84b91dc07d140ac5099f39a/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/code_mixed_jv_id/blob/dc88250f1d1df844f84b91dc07d140ac5099f39a/LICENSE",
 "card_nc": false
}