Package: quanteda
Version: 4.4.1
Title: Quantitative Analysis of Textual Data
Description: A fast, flexible, and comprehensive framework for
        quantitative text analysis in R.  Provides functionality for
        corpus management, creating and manipulating tokens and
        n-grams, exploring keywords in context, forming and
        manipulating sparse matrices of documents by features and
        feature co-occurrences, analyzing keywords, computing feature
        similarities and distances, applying content dictionaries,
        applying supervised and unsupervised machine learning, visually
        representing text and text analyses, and more.
Authors@R: c( 
    person("Kenneth", "Benoit", email = "kbenoit@lse.ac.uk", role = c("cre", "aut", "cph"), comment = c(ORCID = "0000-0002-0797-564X")), 
    person("Kohei", "Watanabe", email = "watanabe.kohei@gmail.com", role = "aut", comment = c(ORCID = "0000-0001-6519-5265")), 
    person("Haiyan", "Wang", email = "whyinsa@yahoo.com", role = "aut", comment = c(ORCID = "0000-0003-4992-4311")),
    person("Paul", "Nulty", email = "paul.nulty@gmail.com", role = "aut", comment = c(ORCID = "0000-0002-7214-4666")), 
    person("Adam", "Obeng", email = "quanteda@binaryeagle.com", role = "aut", comment = c(ORCID = "0000-0002-2906-4775")),
    person("Stefan", "Müller", email = "stefan.mueller@ucd.ie", role = "aut", comment = c(ORCID = "0000-0002-6315-4125")),
    person("Akitaka", "Matsuo", email = "a.matsuo@essex.ac.uk", role = "aut", comment = c(ORCID = "0000-0002-3323-6330")),
    person("William", "Lowe", email = "lowe@hertie-school.org", role = "aut", comment = c(ORCID = "0000-0002-1549-6163")),
    person("Christian", "Müller", email = "C.Mueller@lse.ac.uk", role = "ctb"),
    person("Olivier", "Delmarcelle", email = "olivier.delmarcelle@ugent.be", role = "ctb", comment = c(ORCID = "0000-0003-4347-070X")),
    person("European Research Council", role = "fnd", comment = "ERC-2011-StG 283794-QUANTESS")
    )
License: GPL-3
Depends: R (>= 4.1.0), methods
Imports: fastmatch, jsonlite, lifecycle, magrittr, Matrix (>= 1.5-0),
        Rcpp (>= 0.12.12), SnowballC, stopwords, stringi, xml2, yaml
LinkingTo: Rcpp
NeedsCompilation: yes
Suggests: rmarkdown, spelling, testthat, formatR, tm (>= 0.6), knitr,
        lsa, rlang, slam, torch
Enhances: dplyr, lda, purrr, spacyr, stm, text2vec, tibble, tidytext,
        tokenizers, topicmodels
URL: https://quanteda.io
Encoding: UTF-8
BugReports: https://github.com/quanteda/quanteda/issues
LazyData: TRUE
VignetteBuilder: knitr
Language: en-GB
Roxygen: list(markdown = TRUE)
Collate: 'RcppExports.R' 'tokenizers.R' 'meta.R'
        'quanteda-documentation.R' 'aaa.R' 'bootstrap_dfm.R'
        'casechange-functions.R' 'char_select.R' 'convert.R'
        'corpus-addsummary-metadata.R' 'corpus-methods.R' 'corpus.R'
        'corpus_chunk.R' 'corpus_group.R' 'corpus_reshape.R'
        'corpus_sample.R' 'corpus_segment.R' 'corpus_subset.R'
        'corpus_trim.R' 'data-documentation.R' 'dfm-classes.R'
        'dfm-methods.R' 'dfm-print.R' 'dfm-subsetting.R' 'dfm.R'
        'dfm_compress.R' 'dfm_group.R' 'dfm_lookup.R' 'dfm_match.R'
        'dfm_replace.R' 'dfm_sample.R' 'dfm_select.R' 'dfm_sort.R'
        'dfm_subset.R' 'dfm_trim.R' 'dfm_weight.R' 'dictionaries.R'
        'dimnames.R' 'fcm-classes.R' 'docnames.R' 'docvars.R'
        'fcm-methods.R' 'fcm-print.R' 'fcm-subsetting.R' 'fcm.R'
        'fcm_select.R' 'index.R' 'kwic.R' 'message.R' 'nfunctions.R'
        'object-builder.R' 'object2fixed.R' 'pattern2fixed.R'
        'phrases.R' 'quanteda-package.R' 'quanteda_options.R'
        'spacyr-methods.R' 'stopwords.R' 'summary.R' 'textmodel.R'
        'textplot.R' 'texts.R' 'textstat.R' 'tokens-methods.R'
        'tokens.R' 'tokens_annotate.R' 'tokens_chunk.R'
        'tokens_compound.R' 'tokens_group.R' 'tokens_lookup.R'
        'tokens_ngrams.R' 'tokens_replace.R' 'tokens_restore.R'
        'tokens_sample.R' 'tokens_segment.R' 'tokens_select.R'
        'tokens_split.R' 'tokens_subset.R' 'tokens_trim.R'
        'tokens_xptr.R' 'utils.R' 'validator.R' 'wordstem.R' 'zzz.R'
Config/roxygen2/version: 8.0.0
Config/pak/sysreqs: libicu-dev libxml2-dev
Repository: https://quanteda.r-universe.dev
Date/Publication: 2026-06-10 01:26:03 UTC
RemoteUrl: https://github.com/quanteda/quanteda
RemoteRef: HEAD
RemoteSha: 0dffbfdf564f71e9df20a69aecbc46ae2d3f25dd
Packaged: 2026-06-24 05:31:36 UTC; root
Author: Kenneth Benoit [cre, aut, cph] (ORCID:
    <https://orcid.org/0000-0002-0797-564X>),
  Kohei Watanabe [aut] (ORCID: <https://orcid.org/0000-0001-6519-5265>),
  Haiyan Wang [aut] (ORCID: <https://orcid.org/0000-0003-4992-4311>),
  Paul Nulty [aut] (ORCID: <https://orcid.org/0000-0002-7214-4666>),
  Adam Obeng [aut] (ORCID: <https://orcid.org/0000-0002-2906-4775>),
  Stefan Müller [aut] (ORCID: <https://orcid.org/0000-0002-6315-4125>),
  Akitaka Matsuo [aut] (ORCID: <https://orcid.org/0000-0002-3323-6330>),
  William Lowe [aut] (ORCID: <https://orcid.org/0000-0002-1549-6163>),
  Christian Müller [ctb],
  Olivier Delmarcelle [ctb] (ORCID:
    <https://orcid.org/0000-0003-4347-070X>),
  European Research Council [fnd] (ERC-2011-StG 283794-QUANTESS)
Maintainer: Kenneth Benoit <kbenoit@lse.ac.uk>