{ "_id": "6a589a65ff0138dec5d75a85", "Package": "textdata", "Title": "Download and Load Various Text Datasets", "Version": "0.4.5.9000", "Authors@R": "c(\nperson(\"Emil\", \"Hvitfeldt\", , \"emilhhvitfeldt@gmail.com\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0002-0679-1945\")),\nperson(\"Julia\", \"Silge\", , \"julia.silge@gmail.com\", role = \"ctb\",\ncomment = c(ORCID = \"0000-0002-3671-836X\"))\n)", "Description": "Provides a framework to download, parse, and store text\ndatasets on the disk and load them when needed. Includes\nvarious sentiment lexicons and labeled text data sets for\nclassification and analysis.", "License": "MIT + file LICENSE", "URL": "https://emilhvitfeldt.github.io/textdata/,\nhttps://github.com/EmilHvitfeldt/textdata", "BugReports": "https://github.com/EmilHvitfeldt/textdata/issues", "VignetteBuilder": "knitr", "Encoding": "UTF-8", "RoxygenNote": "7.3.1.9000", "Collate": "'cache_info.R' 'dataset_ag_news.R' 'dataset_dbpedia.R'\n'dataset_imdb.R' 'dataset_sentence_polarity.R' 'dataset_trec.R'\n'embedding_glove.R' 'lexicon_nrc_vad.R' 'lexicon_nrc_eil.R'\n'lexicon_nrc.R' 'lexicon_bing.R' 'lexicon_loughran.R'\n'lexicon_afinn.R' 'download_functions.R' 'info.R'\n'load_dataset.R' 'printer.R' 'process_functions.R'\n'textdata-package.R'", "Config/pak/sysreqs": "cmake make libuv1-dev libx11-dev", "Repository": "https://emilhvitfeldt.r-universe.dev", "Date/Publication": "2024-05-28 22:00:24 UTC", "RemoteUrl": "https://github.com/emilhvitfeldt/textdata", "RemoteRef": "HEAD", "RemoteSha": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "NeedsCompilation": "no", "Packaged": { "Date": "2026-07-16 08:43:16 UTC", "User": "root" }, "Author": "Emil Hvitfeldt [aut, cre] (ORCID:\n),\nJulia Silge [ctb] (ORCID: )", "Maintainer": "Emil Hvitfeldt ", "_user": "emilhvitfeldt", "_type": "src", "_file": "textdata_0.4.5.9000.tar.gz", "_fileid": "https://r2.ropensci.org/86715e140c8eb0a08a4974e1d90ca87bdf19337539d10f6687496c3e507630db", "_filesize": 4777256, "_sha256": "86715e140c8eb0a08a4974e1d90ca87bdf19337539d10f6687496c3e507630db", "_expires": "2026-10-24T08:46:27.000Z", "_created": "2026-07-16T08:43:16.000Z", "_published": "2026-07-16T08:46:29.616Z", "_jobs": [ { "job": 87575589881, "time": 147, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8369859764" }, { "job": 87575589780, "time": 135, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8369855373" }, { "job": 87575589777, "time": 109, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8369845097" }, { "job": 87575589700, "time": 89, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8369836878" }, { "job": 87574887548, "time": 211, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8369801567" }, { "job": 87575589696, "time": 123, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8369850750" }, { "job": 87575589856, "time": 85, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8369835698" }, { "job": 87575589819, "time": 70, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8369830145" }, { "job": 87575589796, "time": 73, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8369830507" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/29484240117", "_status": "success", "_upstream": "https://github.com/emilhvitfeldt/textdata", "_commit": { "id": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "author": "Emil Hvitfeldt ", "committer": "GitHub ", "message": "Merge pull request #58 from EmilHvitfeldt/PC-0.4.5\n\nRelease Candidate 0.4.5", "time": 1716933624 }, "_maintainer": { "name": "Emil Hvitfeldt", "email": "emilhhvitfeldt@gmail.com", "login": "emilhvitfeldt", "bluesky": "@emilhvitfeldt.bsky.social", "description": "All things @tidymodels", "uuid": 14034784, "orcid": "0000-0002-0679-1945" }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "fs", "role": "Imports" }, { "package": "rappdirs", "role": "Imports" }, { "package": "readr", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "covr", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 2.1.0", "role": "Suggests" } ], "_owner": "emilhvitfeldt", "_selfowned": true, "_usedby": 3, "_updates": [], "_tags": [], "_topics": [ "text-datasets" ], "_stars": 78, "_contributors": [ { "user": "emilhvitfeldt", "count": 134, "uuid": 14034784 }, { "user": "juliasilge", "count": 5, "uuid": 12505835 }, { "user": "ellisvalentiner", "count": 1, "uuid": 9932219 }, { "user": "jmclawson", "count": 1, "uuid": 3894072 }, { "user": "jonthegeek", "count": 1, "uuid": 33983824 }, { "user": "olivroy", "count": 1, "uuid": 52606734 } ], "_userbio": { "uuid": 14034784, "type": "user", "name": "Emil Hvitfeldt", "followers": 1056, "description": "All things @tidymodels" }, "_downloads": { "count": 4058, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/textdata" }, "_mentions": 1, "_devurl": "https://github.com/emilhvitfeldt/textdata", "_pkgdown": "https://emilhvitfeldt.github.io/textdata/", "_searchresults": 1916, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/textdata.html", "LICENSE", "manual.pdf" ], "_homeurl": "https://github.com/emilhvitfeldt/textdata", "_realowner": "emilhvitfeldt", "_cranurl": true, "_releases": [ { "version": "0.1.0", "date": "2019-06-12" }, { "version": "0.2.0", "date": "2019-07-22" }, { "version": "0.3.0", "date": "2019-08-28" }, { "version": "0.4.0", "date": "2020-03-06" }, { "version": "0.4.1", "date": "2020-05-04" }, { "version": "0.4.2", "date": "2022-05-02" }, { "version": "0.4.3", "date": "2022-08-15" }, { "version": "0.4.4", "date": "2022-09-02" }, { "version": "0.4.5", "date": "2024-05-28" } ], "_exports": [ "cache_info", "catalogue", "dataset_ag_news", "dataset_dbpedia", "dataset_imdb", "dataset_sentence_polarity", "dataset_trec", "embedding_glove27b", "embedding_glove42b", "embedding_glove6b", "embedding_glove840b", "lexicon_afinn", "lexicon_bing", "lexicon_loughran", "lexicon_nrc", "lexicon_nrc_eil", "lexicon_nrc_vad", "load_dataset" ], "_help": [ { "page": "cache_info", "title": "List folders and their sizes in cache", "topics": [ "cache_info" ] }, { "page": "catalogue", "title": "Catalogue of all available data sources", "topics": [ "catalogue" ] }, { "page": "dataset_ag_news", "title": "AG's News Topic Classification Dataset", "concept": [ "topic" ], "topics": [ "dataset_ag_news" ] }, { "page": "dataset_dbpedia", "title": "DBpedia Ontology Dataset", "concept": [ "topic" ], "topics": [ "dataset_dbpedia" ] }, { "page": "dataset_imdb", "title": "IMDB Large Movie Review Dataset", "concept": [ "topic sentiment" ], "topics": [ "dataset_imdb" ] }, { "page": "dataset_sentence_polarity", "title": "v1.0 sentence polarity dataset", "concept": [ "sentiment" ], "topics": [ "dataset_sentence_polarity" ] }, { "page": "dataset_trec", "title": "TREC dataset", "concept": [ "topic" ], "topics": [ "dataset_trec" ] }, { "page": "embedding_glove", "title": "Global Vectors for Word Representation", "concept": [ "embeddings" ], "topics": [ "embedding_glove", "embedding_glove27b", "embedding_glove42b", "embedding_glove6b", "embedding_glove840b" ] }, { "page": "lexicon_afinn", "title": "AFINN-111 dataset", "concept": [ "lexicon" ], "topics": [ "lexicon_afinn" ] }, { "page": "lexicon_bing", "title": "Bing sentiment lexicon", "concept": [ "lexicon" ], "topics": [ "lexicon_bing" ] }, { "page": "lexicon_loughran", "title": "Loughran-McDonald sentiment lexicon", "concept": [ "lexicon" ], "topics": [ "lexicon_loughran" ] }, { "page": "lexicon_nrc", "title": "NRC word-emotion association lexicon", "concept": [ "lexicon" ], "topics": [ "lexicon_nrc" ] }, { "page": "lexicon_nrc_eil", "title": "NRC Emotion Intensity Lexicon (aka Affect Intensity Lexicon) v0.5", "concept": [ "lexicon" ], "topics": [ "lexicon_nrc_eil" ] }, { "page": "lexicon_nrc_vad", "title": "The NRC Valence, Arousal, and Dominance Lexicon", "concept": [ "lexicon" ], "topics": [ "lexicon_nrc_vad" ] } ], "_pkglogo": "https://github.com/emilhvitfeldt/textdata/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/emilhvitfeldt/textdata/raw/HEAD/README.md", "_rundeps": [ "bit", "bit64", "cli", "clipr", "cpp11", "crayon", "fs", "glue", "hms", "lifecycle", "magrittr", "pillar", "pkgconfig", "prettyunits", "progress", "R6", "rappdirs", "readr", "rlang", "tibble", "tidyselect", "tzdb", "utf8", "vctrs", "vroom", "withr" ], "_vignettes": [ { "source": "How-to-add-a-data-set.Rmd", "filename": "How-to-add-a-data-set.html", "title": "How to add a data set", "engine": "knitr::rmarkdown", "headings": [ "Guidelines for textdata datasets", "Classification datasets" ], "created": "2019-06-08 22:16:31", "modified": "2022-05-02 16:30:06", "commits": 8 } ], "_score": 10.134984668241696, "_indexed": true, "_nocasepkg": "textdata", "_universes": [ "emilhvitfeldt" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.4.5.9000", "date": "2026-07-16T08:45:42.000Z", "distro": "resolute", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "https://r2.ropensci.org/e3657a93cb7b203275ea0b5a6f591cfd13139e0c30e62c3f4873c15207a6cbcd", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/29484240117" }, { "r": "4.6.1", "os": "linux", "version": "0.4.5.9000", "date": "2026-07-16T08:45:30.000Z", "distro": "resolute", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "https://r2.ropensci.org/7aaf32c66e4dfb3173f484dc6ab7402ea1bf43a0c457019b7619ed32b2b1e3d0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/29484240117" }, { "r": "4.5.3", "os": "mac", "version": "0.4.5.9000", "date": "2026-07-16T08:45:04.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "https://r2.ropensci.org/f8fc69de335c6080ba5ca0ba645e3c3b34bfd83ae2d2b93d1964aaf6186dce39", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/29484240117" }, { "r": "4.6.1", "os": "mac", "version": "0.4.5.9000", "date": "2026-07-16T08:44:46.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "https://r2.ropensci.org/5f2088a20d65542f47154aa067394a33640fca1183bb7cfee4e8b56569bf99a1", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/29484240117" }, { "r": "4.6.0", "os": "wasm", "version": "0.4.5.9000", "date": "2026-07-16T08:45:36.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "https://r2.ropensci.org/250d3586a610e4ac664d7d63d8e4229aee087ab3b7c1e73f7ad79e54dc600e01", "status": "success", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/29484240117" }, { "r": "4.7.0", "os": "win", "version": "0.4.5.9000", "date": "2026-07-16T08:44:34.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "https://r2.ropensci.org/00a00b0da80ea51e8298a65d12e69cd4f70cb044f68a53e1e27a95ffad8aea23", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/29484240117" }, { "r": "4.5.3", "os": "win", "version": "0.4.5.9000", "date": "2026-07-16T08:44:22.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "https://r2.ropensci.org/837e2bfb9ac0ef07b67f62e8451a6d2c761e9cf55ef5294c2a66d327e75a4d1d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/29484240117" }, { "r": "4.6.1", "os": "win", "version": "0.4.5.9000", "date": "2026-07-16T08:44:21.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "https://r2.ropensci.org/2e37f7598da62d07eabf6e87d604052f5a4b18215dc3cc27830291f57374a3df", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/29484240117" } ] }