{ "_id": "6ab7983499f7aa8c6aa32a08", "Package": "textclassificationtutorial", "Title": "Reproducible Text Classification Workflows", "Version": "0.1.2", "Authors@R": "c(\nperson(\"Vladimer\", \"Kobayashi\", role = c(\"aut\", \"cre\"),\nemail = \"vladimer.kobayashi@gmail.com\"),\nperson(\"Stefan\", \"Mol\", role = \"aut\"),\nperson(\"Gabor\", \"Kismihok\", role = \"aut\")\n)", "Description": "Dependency-light tools and tutorials for teaching\nreproducible text classification. The package covers HTML text\nextraction, sentence segmentation, text preprocessing,\ndocument-term matrices, TF-IDF, keyword extraction, cosine\nsimilarity, stratified cross-validation, classification\nmetrics, and a multinomial Naive Bayes classifier. It\nmodernizes the code accompanying Kobayashi, V. B., Berkers, H.\nA., Mol, S. T. Kismihok, G., and Den Hartog, D. N. (2017)\n The package replaces the\noriginal scripts in the paper.", "License": "Apache License (>= 2)", "URL": "https://github.com/vkobayashi/textclassificationtutorial", "BugReports": "https://github.com/vkobayashi/textclassificationtutorial/issues", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "Encoding": "UTF-8", "Config/roxygen2/version": "8.0.0", "NeedsCompilation": "no", "Packaged": { "Date": "2026-09-26 09:58:27 UTC", "User": "root" }, "Author": "Vladimer Kobayashi [aut, cre], Stefan Mol [aut], Gabor Kismihok\n[aut]", "Maintainer": "Vladimer Kobayashi ", "Repository": "https://vkobayashi.r-universe.dev", "Date/Publication": "2026-08-26 20:15:00 UTC", "RemoteUrl": "https://github.com/cran/textclassificationtutorial", "RemoteRef": "HEAD", "RemoteSha": "9338ed09b2bfd2b66a96c44a79608b1499be39d0", "_user": "vkobayashi", "_type": "src", "_file": "textclassificationtutorial_0.1.2.tar.gz", "_fileid": "https://r2.ropensci.org/8c0836a7cb1753ec885467d377010a4389ba2f08160500b4ea3f7f75ea2aa9c6", "_filesize": 188484, "_sha256": "8c0836a7cb1753ec885467d377010a4389ba2f08160500b4ea3f7f75ea2aa9c6", "_expires": "2027-01-04T10:02:26.000Z", "_created": "2026-09-26T09:58:27.000Z", "_published": "2026-09-26T10:02:28.118Z", "_jobs": [ { "job": 108383392428, "time": 122, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "10904040153" }, { "job": 108383392399, "time": 119, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "10902879945" }, { "job": 108383392437, "time": 194, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "10903617386" }, { "job": 108383392628, "time": 150, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "10904030222" }, { "job": 108382953399, "time": 201, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "10903871356" }, { "job": 108383392422, "time": 102, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "10903602426" }, { "job": 108383392493, "time": 77, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "10903747056" }, { "job": 108383392446, "time": 66, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "10903936060" }, { "job": 108383392542, "time": 68, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "10902979689" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/vkobayashi/actions/runs/36234206854", "_status": "success", "_upstream": "https://github.com/cran/textclassificationtutorial", "_commit": { "id": "9338ed09b2bfd2b66a96c44a79608b1499be39d0", "author": "Vladimer Kobayashi ", "committer": "cran-robot ", "message": "version 0.1.2\n", "time": 1787775300 }, "_maintainer": { "name": "Vladimer Kobayashi", "email": "vladimer.kobayashi@gmail.com", "login": "vkobayashi", "description": "", "uuid": 1955218 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1.0", "role": "Depends" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "xml2", "role": "Suggests" } ], "_owner": "cran", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-35", "n": 1 } ], "_tags": [ { "name": "0.1.2", "date": "2026-08-26" } ], "_stars": 0, "_contributors": [ { "user": "vkobayashi", "count": 1, "uuid": 1955218 } ], "_userbio": { "uuid": 1955218, "type": "user", "name": "Vladimer Kobayashi", "followers": 2 }, "_downloads": { "count": 355, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/textclassificationtutorial" }, "_devurl": "https://github.com/vkobayashi/textclassificationtutorial", "_searchresults": 0, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/textclassificationtutorial.html" ], "_realowner": "vkobayashi", "_cranurl": false, "_releases": [ { "version": "0.1.2", "date": "2026-08-26" } ], "_exports": [ "classification_metrics", "cosine_similarity", "document_term_matrix", "extract_html_dir", "extract_html_text", "extract_keywords", "f_measure", "fit_naive_bayes", "preprocess_text", "read_label_file", "split_sentences", "stratified_folds", "tf_idf" ], "_help": [ { "page": "classification_metrics", "title": "Calculate binary classification metrics", "topics": [ "classification_metrics" ] }, { "page": "cosine_similarity", "title": "Compute cosine similarity", "topics": [ "cosine_similarity" ] }, { "page": "document_term_matrix", "title": "Construct a document-term matrix", "topics": [ "document_term_matrix" ] }, { "page": "extract_html_dir", "title": "Extract text from a directory of HTML files", "topics": [ "extract_html_dir" ] }, { "page": "extract_html_text", "title": "Extract readable text from HTML", "topics": [ "extract_html_text" ] }, { "page": "extract_keywords", "title": "Extract top TF-IDF keywords", "topics": [ "extract_keywords" ] }, { "page": "f_measure", "title": "F-measure", "topics": [ "f_measure" ] }, { "page": "fit_naive_bayes", "title": "Fit a multinomial Naive Bayes text classifier", "topics": [ "fit_naive_bayes" ] }, { "page": "preprocess_text", "title": "Normalize text for document-term analysis", "topics": [ "preprocess_text" ] }, { "page": "read_label_file", "title": "Read a one-label-per-line file", "topics": [ "read_label_file" ] }, { "page": "split_sentences", "title": "Split text into sentences", "topics": [ "split_sentences" ] }, { "page": "stratified_folds", "title": "Create stratified cross-validation folds", "topics": [ "stratified_folds" ] }, { "page": "tf_idf", "title": "Calculate TF-IDF weights", "topics": [ "tf_idf" ] } ], "_readme": "https://github.com/cran/textclassificationtutorial/raw/HEAD/README.md", "_rundeps": [], "_vignettes": [ { "source": "model-evaluation.Rmd", "filename": "model-evaluation.html", "title": "Evaluating a Text Classifier", "engine": "knitr::rmarkdown", "headings": [ "Why evaluation design matters", "Stratified folds", "Cross-validation loop", "Interpret the metrics", "From tutorial to research" ], "created": "2026-08-26 20:15:00", "modified": "2026-08-26 20:15:00", "commits": 1 }, { "source": "getting-started.Rmd", "filename": "getting-started.html", "title": "Getting Started with Text Classification", "engine": "knitr::rmarkdown", "headings": [ "Overview", "Extract text from HTML", "Segment and normalize", "Create document features", "Explore similarity", "Train a classifier", "Reproducible research checklist" ], "created": "2026-08-26 20:15:00", "modified": "2026-08-26 20:15:00", "commits": 1 } ], "_score": 3, "_indexed": true, "_nocasepkg": "textclassificationtutorial", "_universes": [ "vkobayashi" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.2", "date": "2026-09-26T10:00:34.000Z", "distro": "resolute", "commit": "9338ed09b2bfd2b66a96c44a79608b1499be39d0", "fileid": "https://r2.ropensci.org/2fcc85c409118bb87fa4828467c0618ef6397e29394a4fb924ae64fe0c6018ac", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/vkobayashi/actions/runs/36234206854" }, { "r": "4.6.1", "os": "linux", "version": "0.1.2", "date": "2026-09-26T10:00:32.000Z", "distro": "resolute", "commit": "9338ed09b2bfd2b66a96c44a79608b1499be39d0", "fileid": "https://r2.ropensci.org/6ddb31447529a64cca571a602654a5518c198b213cc1328ae95a00f9f499d61c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/vkobayashi/actions/runs/36234206854" }, { "r": "4.5.3", "os": "mac", "version": "0.1.2", "date": "2026-09-26T10:01:08.000Z", "commit": "9338ed09b2bfd2b66a96c44a79608b1499be39d0", "fileid": "https://r2.ropensci.org/6390c85b32cce6f870d1c6861472b6b26b83ac4d0447228852aae8df194cf545", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/vkobayashi/actions/runs/36234206854" }, { "r": "4.6.1", "os": "mac", "version": "0.1.2", "date": "2026-09-26T10:00:39.000Z", "commit": "9338ed09b2bfd2b66a96c44a79608b1499be39d0", "fileid": "https://r2.ropensci.org/0c14377a488302578fca509fea2ed2b49b6c557ce8939b89104637c543878ad5", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/vkobayashi/actions/runs/36234206854" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.2", "date": "2026-09-26T10:00:26.000Z", "commit": "9338ed09b2bfd2b66a96c44a79608b1499be39d0", "fileid": "https://r2.ropensci.org/71c66cd091a455d113f87bc4c585ad1a3ffb509dc3b979ce19bb9e6fed381583", "status": "success", "buildurl": "https://github.com/r-universe/vkobayashi/actions/runs/36234206854" }, { "r": "4.7.0", "os": "win", "version": "0.1.2", "date": "2026-09-26T09:59:41.000Z", "commit": "9338ed09b2bfd2b66a96c44a79608b1499be39d0", "fileid": "https://r2.ropensci.org/8cd52526ae1a5e55cebc01679c298dbf9f41ef915b3fec3b06a95324a5ecbbf0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/vkobayashi/actions/runs/36234206854" }, { "r": "4.5.3", "os": "win", "version": "0.1.2", "date": "2026-09-26T09:59:34.000Z", "commit": "9338ed09b2bfd2b66a96c44a79608b1499be39d0", "fileid": "https://r2.ropensci.org/ea595f5903b44ccbc94f9b5cb74c51caa47d2933a39ff3035ebe3f4106d23630", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/vkobayashi/actions/runs/36234206854" }, { "r": "4.6.1", "os": "win", "version": "0.1.2", "date": "2026-09-26T09:59:34.000Z", "commit": "9338ed09b2bfd2b66a96c44a79608b1499be39d0", "fileid": "https://r2.ropensci.org/e9ae5f0aa17703de4e708954d6efcb75e98604b61c3ff4ccfbbf34f366d0b929", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/vkobayashi/actions/runs/36234206854" } ] }