{
 "id": "Se7sinBlackbird/site_tags",
 "owner": "Se7sinBlackbird",
 "name": "site_tags",
 "downloads": 207,
 "likes": 0,
 "last_modified": "2026-06-12T07:02:30.000Z",
 "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",
  "text-retrieval",
  "feature-extraction"
 ],
 "citation": "@misc{site_tags_dataset,\n  title        = {Site Tags Dataset Collection: Comprehensive Tag Metadata from Image Hosting Platforms},\n  author       = {deepghs},\n  howpublished = {\\url{https://huggingface.co/datasets/deepghs/site_tags}},\n  year         = {2024},\n  note         = {A unified collection of structured tag metadata from 18 popular image hosting and booru websites, enabling multilingual tag analysis and content classification research},\n  abstract     = {This comprehensive dataset collection provides structured tag metadata from 18 popular image hosting and booru websites, offering a unified repository for multilingual tag analysis and content classification. The dataset encompasses over 2.5 million unique tags across various platforms including Danbooru, Gelbooru, Pixiv, Sankaku Complex, and Wallhaven, making it one of the most extensive collections of image annotation metadata available. Each platform's tags are provided in multiple formats including JSON, CSV, Parquet, and SQLite databases, ensuring compatibility with diverse data processing workflows. The dataset captures rich semantic relationships between tags through various metadata fields such as tag categories, post counts, aliases, and hierarchical relationships.},\n  keywords     = {tags, metadata, image-tagging, booru, dataset, multilingual}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "b9e1958a8202db490e45c1626443269d868f7997",
 "stated_evidence": "https://huggingface.co/datasets/Se7sinBlackbird/site_tags/blob/b9e1958a8202db490e45c1626443269d868f7997/README.md",
 "file_evidence": "https://huggingface.co/datasets/Se7sinBlackbird/site_tags/tree/b9e1958a8202db490e45c1626443269d868f7997",
 "card_nc": false
}