{"id":19420359,"url":"https://github.com/hantang/data-corpus","last_synced_at":"2026-02-13T21:33:39.771Z","repository":{"id":268918582,"uuid":"832908155","full_name":"hantang/data-corpus","owner":"hantang","description":"语料数据和词库收集：中文、英文停用词，情感分析，分类词典，敏感词库（违禁词，审查词）。stop words, sentiment analysis, thesaurus, censorship/sensitive word","archived":false,"fork":false,"pushed_at":"2026-02-09T05:56:08.000Z","size":107802,"stargazers_count":34,"open_issues_count":0,"forks_count":7,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-02-09T11:40:34.191Z","etag":null,"topics":["corpus","nlp","stopwords","thesaurus"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hantang.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-07-24T01:21:37.000Z","updated_at":"2026-02-09T05:56:16.000Z","dependencies_parsed_at":null,"dependency_job_id":"ab12fa8d-e4a5-4460-af09-e8f049f8323c","html_url":"https://github.com/hantang/data-corpus","commit_stats":null,"previous_names":["hantang/data-corpus"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hantang/data-corpus","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hantang%2Fdata-corpus","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hantang%2Fdata-corpus/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hantang%2Fdata-corpus/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hantang%2Fdata-corpus/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hantang","download_url":"https://codeload.github.com/hantang/data-corpus/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hantang%2Fdata-corpus/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29418533,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-13T06:24:03.484Z","status":"ssl_error","status_checked_at":"2026-02-13T06:23:12.830Z","response_time":78,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["corpus","nlp","stopwords","thesaurus"],"created_at":"2024-11-10T13:22:44.692Z","updated_at":"2026-02-13T21:33:39.730Z","avatar_url":"https://github.com/hantang.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# corpus\n\nNLP 词库汇集 （备份）：\n- 多种语言的停用词（stop words），\n- 情感分析（sentiment），\n- 分类词典 （thesaurus），\n- 审查词库（敏感词/违禁词，censorship/sensitive words）\n- ……\n\n来源详见：[CHANGELOG](./CHANGELOG.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhantang%2Fdata-corpus","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhantang%2Fdata-corpus","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhantang%2Fdata-corpus/lists"}