{
"_id": "6ae331b93d0f299392dd1285",
"Type": "Package",
"Package": "acR",
"Title": "Content Analysis in R: Integrated Qualitative (LLMs) and\nQuantitative Pipeline",
"Version": "0.6.1",
"Authors@R": "person(\"Anderson Henrique\", email = \"anderson.henrique@usp.br\",\nrole = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0002-1842-2725\"))",
"Description": "Provides an integrated pipeline for content analysis\ncombining qualitative coding assisted by large language models\n(LLMs) with classical quantitative text analysis. Includes\nmodules for pre-processing (tokenization, stopwords for\nBrazilian Portuguese), descriptive statistics, keyness,\nco-occurrence networks, word clouds (including comparative and\nX-ray variants), sentiment analysis via OpLexicon, Latent\nDirichlet Allocation (LDA), inter-coder reliability metrics\n(Krippendorff, Gwet), and modern visualizations based on\nggplot2. Special focus on Brazilian corpora and\npolitical-institutional codebooks. Inspired by Maerz and Benoit\n(2025) .",
"License": "MIT + file LICENSE",
"URL": "https://github.com/andersonheri/acR, https://ahenriquecp.com/acR/",
"BugReports": "https://github.com/andersonheri/acR/issues",
"VignetteBuilder": "knitr",
"Config/testthat/edition": "3",
"Encoding": "UTF-8",
"Language": "en-US",
"Roxygen": "list(markdown = TRUE)",
"RoxygenNote": "7.3.2",
"Config/pak/sysreqs": "libicu-dev libssl-dev",
"Repository": "https://andersonheri.r-universe.dev",
"Date/Publication": "2026-10-29 02:54:56 UTC",
"RemoteUrl": "https://github.com/andersonheri/acr",
"RemoteRef": "HEAD",
"RemoteSha": "46f6bf9bfc1cfd28a828b9a4279160cfa0e26576",
"NeedsCompilation": "no",
"Packaged": {
"Date": "2026-10-29 10:52:17 UTC",
"User": "root"
},
"Author": "Anderson Henrique [aut, cre] (ORCID:\n)",
"Maintainer": "Anderson Henrique ",
"_user": "andersonheri",
"_type": "src",
"_file": "acR_0.6.1.tar.gz",
"_fileid": "https://r2.ropensci.org/64d487640695b4f211fb99e6316e8defdbbc231b650416896a4e0bf96b5ae63a",
"_filesize": 6109992,
"_sha256": "64d487640695b4f211fb99e6316e8defdbbc231b650416896a4e0bf96b5ae63a",
"_expires": "2027-02-06T11:44:55.000Z",
"_created": "2026-10-29T10:52:17.000Z",
"_published": "2026-10-29T11:44:57.585Z",
"_upstream": "https://github.com/andersonheri/acr",
"_status": "success",
"_maintainer": {
"name": "Anderson Henrique",
"email": "anderson.henrique@usp.br",
"orcid": "0000-0002-1842-2725"
},
"_jobs": [
{
"job": 123403948150,
"time": 248,
"config": "linux-devel-x86_64",
"r": "4.7.0",
"check": "OK",
"artifact": "12891717286"
},
{
"job": 123403948342,
"time": 244,
"config": "linux-release-x86_64",
"r": "4.6.1",
"check": "OK",
"artifact": "12891148099"
},
{
"job": 123403948135,
"time": 217,
"config": "macos-oldrel-arm64",
"r": "4.5.3",
"check": "OK",
"artifact": "12893299255"
},
{
"job": 123403948062,
"time": 199,
"config": "macos-release-arm64",
"r": "4.6.1",
"check": "OK",
"artifact": "12894227855"
},
{
"job": 123400368620,
"time": 474,
"config": "source",
"r": "4.6.1",
"check": "OK",
"artifact": "12891113238"
},
{
"job": 123403947941,
"time": 161,
"config": "wasm-release",
"r": "4.6.0",
"check": "OK",
"artifact": "12892075998"
},
{
"job": 123403948157,
"time": 179,
"config": "windows-devel-x86_64",
"r": "4.7.0",
"check": "OK",
"artifact": "12892255256"
},
{
"job": 123403948079,
"time": 209,
"config": "windows-oldrel-x86_64",
"r": "4.5.3",
"check": "OK",
"artifact": "12891851749"
},
{
"job": 123403948250,
"time": 199,
"config": "windows-release-x86_64",
"r": "4.6.1",
"check": "OK",
"artifact": "12891637397"
}
],
"_buildurl": "https://github.com/r-universe/andersonheri/actions/runs/40859848273",
"_commit": {
"id": "46f6bf9bfc1cfd28a828b9a4279160cfa0e26576",
"author": "Anderson Henrique, Ph.D. <38498432+andersonheri@users.noreply.github.com>",
"committer": "GitHub ",
"message": "Merge pull request #16 from andersonheri/chore/release-0.6.1\n\nRelease 0.6.1",
"time": 1793242496
},
"_distro": "resolute",
"_host": "GitHub-Actions",
"_registered": true,
"_dependencies": [
{
"package": "R",
"version": ">= 4.1",
"role": "Depends"
},
{
"package": "cli",
"role": "Imports"
},
{
"package": "dplyr",
"role": "Imports"
},
{
"package": "httr2",
"role": "Imports"
},
{
"package": "irr",
"role": "Imports"
},
{
"package": "jsonlite",
"role": "Imports"
},
{
"package": "purrr",
"role": "Imports"
},
{
"package": "rlang",
"role": "Imports"
},
{
"package": "stats",
"role": "Imports"
},
{
"package": "stringr",
"role": "Imports"
},
{
"package": "tibble",
"role": "Imports"
},
{
"package": "tidyr",
"role": "Imports"
},
{
"package": "tidyselect",
"role": "Imports"
},
{
"package": "utils",
"role": "Imports"
},
{
"package": "withr",
"role": "Imports"
},
{
"package": "yaml",
"role": "Imports"
},
{
"package": "callr",
"role": "Suggests"
},
{
"package": "cluster",
"role": "Suggests"
},
{
"package": "covr",
"role": "Suggests"
},
{
"package": "ellmer",
"role": "Suggests"
},
{
"package": "ggplot2",
"role": "Suggests"
},
{
"package": "ggraph",
"role": "Suggests"
},
{
"package": "ggwordcloud",
"role": "Suggests"
},
{
"package": "igraph",
"role": "Suggests"
},
{
"package": "ipeaplot",
"role": "Suggests"
},
{
"package": "knitr",
"role": "Suggests"
},
{
"package": "shiny",
"role": "Suggests"
},
{
"package": "openxlsx",
"role": "Suggests"
},
{
"package": "pkgdown",
"role": "Suggests"
},
{
"package": "quanteda",
"role": "Suggests"
},
{
"package": "readtext",
"role": "Suggests"
},
{
"package": "rmarkdown",
"role": "Suggests"
},
{
"package": "scales",
"role": "Suggests"
},
{
"package": "senatebR",
"role": "Suggests"
},
{
"package": "spelling",
"role": "Suggests"
},
{
"package": "stopwords",
"role": "Suggests"
},
{
"package": "stringi",
"role": "Suggests"
},
{
"package": "tesseract",
"role": "Suggests"
},
{
"package": "testthat",
"role": "Suggests"
},
{
"package": "tidytext",
"role": "Suggests"
},
{
"package": "topicmodels",
"role": "Suggests"
},
{
"package": "wordcloud",
"role": "Suggests"
},
{
"package": "writexl",
"role": "Suggests"
}
],
"_owner": "andersonheri",
"_selfowned": true,
"_usedby": 0,
"_updates": [
{
"week": "2026-16",
"n": 61
},
{
"week": "2026-17",
"n": 12
},
{
"week": "2026-29",
"n": 40
},
{
"week": "2026-31",
"n": 3
},
{
"week": "2026-32",
"n": 7
},
{
"week": "2026-34",
"n": 1
},
{
"week": "2026-37",
"n": 1
},
{
"week": "2026-38",
"n": 2
},
{
"week": "2026-42",
"n": 40
},
{
"week": "2026-44",
"n": 5
}
],
"_tags": [
{
"name": "v0.0.0.9001",
"date": "2026-04-16"
}
],
"_stars": 4,
"_contributors": [
{
"user": "andersonheri",
"count": 141,
"uuid": 38498432
},
{
"user": "claude",
"count": 69,
"uuid": 81847
}
],
"_userbio": {
"uuid": 38498432,
"type": "user",
"name": "Anderson Henrique, Ph.D. ",
"followers": 16,
"description": "Post Doctoral Researcher in Political Science at Center of Studies of the Metropoles // Ph.D in Political Science (UFPE - Brazil)."
},
"_downloads": {
"count": 581,
"source": "https://cranlogs.r-pkg.org/downloads/total/last-month/acR"
},
"_devurl": "https://github.com/andersonheri/acr",
"_pkgdown": "https://ahenriquecp.com/acR/",
"_searchresults": 25,
"_rbuild": "4.6.1",
"_assets": [
"extra/acR.html",
"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",
"LICENSE"
],
"_homeurl": "https://github.com/andersonheri/acr",
"_realowner": "andersonheri",
"_cranurl": true,
"_releases": [
{
"version": "0.3.2",
"date": "2026-08-07"
},
{
"version": "0.3.3",
"date": "2026-08-20"
},
{
"version": "0.3.4",
"date": "2026-09-10"
},
{
"version": "0.4.0",
"date": "2026-10-14"
},
{
"version": "0.6.0",
"date": "2026-10-16"
}
],
"_exports": [
"ac_build_dictionary",
"ac_ca",
"ac_calibrate_tokens",
"ac_chat_local",
"ac_clean",
"ac_clean_stopwords",
"ac_cluster_documents",
"ac_collocations",
"ac_cooccurrence",
"ac_corpus",
"ac_count",
"ac_dictionary",
"ac_dictionary_import",
"ac_dictionary_load",
"ac_dictionary_save",
"ac_dictionary_validate",
"ac_emotion",
"ac_estimate_tokens",
"ac_export",
"ac_fetch_camara",
"ac_fetch_senado",
"ac_import",
"ac_keyness",
"ac_kwic",
"ac_lda",
"ac_lda_tune",
"ac_lexical_diversity",
"ac_palette",
"ac_plot_ca",
"ac_plot_cluster",
"ac_plot_cooccurrence",
"ac_plot_keyness",
"ac_plot_lda_topics",
"ac_plot_lda_tune",
"ac_plot_lexical_diversity",
"ac_plot_readability",
"ac_plot_sentiment",
"ac_plot_temporal",
"ac_plot_tf_idf",
"ac_plot_top_terms",
"ac_plot_wordcloud_comparative",
"ac_plot_wordscores",
"ac_plot_xray",
"ac_plot_zipf",
"ac_qual_code",
"ac_qual_codebook",
"ac_qual_codebook_add",
"ac_qual_codebook_history",
"ac_qual_codebook_hybrid",
"ac_qual_codebook_merge",
"ac_qual_codebook_remove",
"ac_qual_codebook_translate",
"ac_qual_export_for_review",
"ac_qual_import_human",
"ac_qual_irr",
"ac_qual_list_models",
"ac_qual_load_codebook",
"ac_qual_recommend_model",
"ac_qual_reliability",
"ac_qual_report",
"ac_qual_report_full",
"ac_qual_sample",
"ac_qual_save_codebook",
"ac_qual_search_literature",
"ac_readability",
"ac_sentiment",
"ac_temporal",
"ac_tf_idf",
"ac_tokenize",
"ac_top_terms",
"ac_wordcloud",
"ac_wordscores",
"as_prompt",
"is_ac_corpus",
"theme_ac"
],
"_help": [
{
"page": "ac_build_dictionary",
"title": "Construir um dicionário multi-categoria",
"concept": [
"quantitative"
],
"topics": [
"ac_build_dictionary"
]
},
{
"page": "ac_ca",
"title": "Análise de correspondência (CA) entre documentos/grupos e termos",
"concept": [
"quantitative"
],
"topics": [
"ac_ca"
]
},
{
"page": "ac_calibrate_tokens",
"title": "Calibrar a razao caracteres/token contra um modelo real",
"concept": [
"qualitative"
],
"topics": [
"ac_calibrate_tokens"
]
},
{
"page": "ac_chat_local",
"title": "Conectar a um servidor LLM local compativel com OpenAI",
"concept": [
"qualitative"
],
"topics": [
"ac_chat_local"
]
},
{
"page": "ac_clean",
"title": "Limpar e normalizar texto de um corpus",
"concept": [
"corpus"
],
"topics": [
"ac_clean"
]
},
{
"page": "ac_clean_stopwords",
"title": "Inspecionar e editar stopwords extras do acR",
"topics": [
"ac_clean_stopwords"
]
},
{
"page": "ac_cluster_documents",
"title": "Agrupamento não supervisionado de documentos",
"concept": [
"quantitative"
],
"topics": [
"ac_cluster_documents"
]
},
{
"page": "ac_collocations",
"title": "Identificar colocações com medidas de associação estatística",
"concept": [
"quantitative"
],
"topics": [
"ac_collocations"
]
},
{
"page": "ac_cooccurrence",
"title": "Calcular co-ocorrências de termos",
"concept": [
"quantitative"
],
"topics": [
"ac_cooccurrence"
]
},
{
"page": "ac_corpus",
"title": "Construir um corpus para análise de conteúdo",
"concept": [
"corpus"
],
"topics": [
"ac_corpus"
]
},
{
"page": "ac_count",
"title": "Contar frequências de tokens ou n-gramas em um corpus",
"concept": [
"corpus"
],
"topics": [
"ac_count"
]
},
{
"page": "ac_dictionary",
"title": "Classificar conteúdo com um dicionário multi-categoria",
"concept": [
"quantitative"
],
"topics": [
"ac_dictionary"
]
},
{
"page": "ac_dictionary_import",
"title": "Importar um dicionário de uma tabela em formato longo",
"concept": [
"quantitative"
],
"topics": [
"ac_dictionary_import"
]
},
{
"page": "ac_dictionary_save",
"title": "Salvar ou carregar um dicionário em YAML",
"concept": [
"quantitative"
],
"topics": [
"ac_dictionary_load",
"ac_dictionary_save"
]
},
{
"page": "ac_dictionary_validate",
"title": "Validar um dicionário contra codificação humana",
"concept": [
"quantitative"
],
"topics": [
"ac_dictionary_validate"
]
},
{
"page": "ac_emotion",
"title": "Classificar emoções com um léxico de palavra-emoção",
"concept": [
"quantitative"
],
"topics": [
"ac_emotion"
]
},
{
"page": "ac_estimate_tokens",
"title": "Estimar número de tokens de um texto",
"concept": [
"qualitative"
],
"topics": [
"ac_estimate_tokens"
]
},
{
"page": "ac_export",
"title": "Exporta resultados de análise de conteúdo em múltiplos formatos",
"topics": [
"ac_export"
]
},
{
"page": "ac_fetch_camara",
"title": "Busca discursos de deputados federais via API da Camara dos Deputados",
"topics": [
"ac_fetch_camara"
]
},
{
"page": "ac_fetch_senado",
"title": "Busca discursos de senadores federais via senatebR",
"topics": [
"ac_fetch_senado"
]
},
{
"page": "ac_import",
"title": "Importar arquivos para um corpus acR",
"topics": [
"ac_import"
]
},
{
"page": "ac_keyness",
"title": "Calcular estatísticas de keyness entre dois grupos",
"concept": [
"corpus"
],
"topics": [
"ac_keyness"
]
},
{
"page": "ac_kwic",
"title": "Concordância (keyword-in-context, KWIC)",
"concept": [
"quantitative"
],
"topics": [
"ac_kwic"
]
},
{
"page": "ac_lda",
"title": "Ajustar modelo LDA (Latent Dirichlet Allocation)",
"concept": [
"quantitative"
],
"topics": [
"ac_lda"
]
},
{
"page": "ac_lda_tune",
"title": "Ajustar múltiplos modelos LDA para selecionar k",
"concept": [
"quantitative"
],
"topics": [
"ac_lda_tune"
]
},
{
"page": "ac_lexical_diversity",
"title": "Calcular diversidade lexical (riqueza de vocabulário)",
"concept": [
"quantitative"
],
"topics": [
"ac_lexical_diversity"
]
},
{
"page": "ac_palette",
"title": "Paleta categórica do acR",
"concept": [
"visualization"
],
"topics": [
"ac_palette"
]
},
{
"page": "ac_plot_ca",
"title": "Visualizar um biplot de análise de correspondência",
"concept": [
"quantitative"
],
"topics": [
"ac_plot_ca"
]
},
{
"page": "ac_plot_cluster",
"title": "Visualiza um objeto ac_cluster",
"concept": [
"visualization"
],
"topics": [
"ac_plot_cluster"
]
},
{
"page": "ac_plot_cooccurrence",
"title": "Visualizar rede de co-ocorrência de termos",
"concept": [
"visualization"
],
"topics": [
"ac_plot_cooccurrence"
]
},
{
"page": "ac_plot_keyness",
"title": "Plotar estatísticas de keyness",
"concept": [
"corpus"
],
"topics": [
"ac_plot_keyness"
]
},
{
"page": "ac_plot_lda_topics",
"title": "Visualizar top termos por tópico",
"concept": [
"visualization"
],
"topics": [
"ac_plot_lda_topics"
]
},
{
"page": "ac_plot_lda_tune",
"title": "Visualizar curva de seleção de k (perplexidade)",
"concept": [
"visualization"
],
"topics": [
"ac_plot_lda_tune"
]
},
{
"page": "ac_plot_lexical_diversity",
"title": "Visualizar diversidade lexical por grupo",
"concept": [
"visualization"
],
"topics": [
"ac_plot_lexical_diversity"
]
},
{
"page": "ac_plot_readability",
"title": "Visualizar legibilidade por grupo",
"concept": [
"visualization"
],
"topics": [
"ac_plot_readability"
]
},
{
"page": "ac_plot_sentiment",
"title": "Visualizar sentimento ao longo dos documentos",
"concept": [
"visualization"
],
"topics": [
"ac_plot_sentiment"
]
},
{
"page": "ac_plot_temporal",
"title": "Visualizar uma série temporal de conteúdo",
"concept": [
"visualization"
],
"topics": [
"ac_plot_temporal"
]
},
{
"page": "ac_plot_tf_idf",
"title": "Plotar termos mais caracteristicos por tf-idf",
"concept": [
"corpus"
],
"topics": [
"ac_plot_tf_idf"
]
},
{
"page": "ac_plot_top_terms",
"title": "Plotar termos mais frequentes",
"concept": [
"corpus"
],
"topics": [
"ac_plot_top_terms"
]
},
{
"page": "ac_plot_wordcloud_comparative",
"title": "Nuvem de palavras comparativa entre grupos",
"concept": [
"visualization"
],
"topics": [
"ac_plot_wordcloud_comparative"
]
},
{
"page": "ac_plot_wordscores",
"title": "Visualizar escores Wordscores por documento",
"concept": [
"quantitative"
],
"topics": [
"ac_plot_wordscores"
]
},
{
"page": "ac_plot_xray",
"title": "Gráfico X-ray: dispersão lexical de termos no corpus",
"concept": [
"visualization"
],
"topics": [
"ac_plot_xray"
]
},
{
"page": "ac_plot_zipf",
"title": "Visualizar a Lei de Zipf (frequência × posto)",
"concept": [
"visualization"
],
"topics": [
"ac_plot_zipf"
]
},
{
"page": "ac_qual_code",
"title": "Classificar textos com LLM usando um codebook",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_code"
]
},
{
"page": "ac_qual_codebook",
"title": "Criar um codebook para análise de conteúdo qualitativa",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_codebook"
]
},
{
"page": "ac_qual_codebook_add",
"title": "Adicionar categoria a um codebook existente",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_codebook_add"
]
},
{
"page": "ac_qual_codebook_history",
"title": "Exibir histórico de modificações de um codebook",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_codebook_history"
]
},
{
"page": "ac_qual_codebook_hybrid",
"title": "Enriquecer codebook com literatura via LLM (modo híbrido)",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_codebook_hybrid"
]
},
{
"page": "ac_qual_codebook_merge",
"title": "Fundir dois codebooks em um",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_codebook_merge"
]
},
{
"page": "ac_qual_codebook_remove",
"title": "Remover categoria de um codebook existente",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_codebook_remove"
]
},
{
"page": "ac_qual_codebook_translate",
"title": "Traduzir codebook para outro idioma via LLM",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_codebook_translate"
]
},
{
"page": "ac_qual_export_for_review",
"title": "Exportar amostra para revisão humana em Excel",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_export_for_review"
]
},
{
"page": "ac_qual_import_human",
"title": "Importar classificação humana de Excel",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_import_human"
]
},
{
"page": "ac_qual_irr",
"title": "Calcular métricas de confiabilidade inter-anotador",
"topics": [
"ac_qual_irr"
]
},
{
"page": "ac_qual_list_models",
"title": "Listar modelos LLM disponíveis para análise de conteúdo",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_list_models"
]
},
{
"page": "ac_qual_load_codebook",
"title": "Carregar codebook de arquivo YAML",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_load_codebook"
]
},
{
"page": "ac_qual_recommend_model",
"title": "Recomendar modelo LLM para análise de conteúdo qualitativa",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_recommend_model"
]
},
{
"page": "ac_qual_reliability",
"title": "Calcular confiabilidade entre codificação LLM e humana",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_reliability"
]
},
{
"page": "ac_qual_report",
"title": "Gerar relatório de replicabilidade da análise qualitativa",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_report"
]
},
{
"page": "ac_qual_report_full",
"title": "Gerar relatório consolidado de múltiplas variáveis de conteúdo",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_report_full"
]
},
{
"page": "ac_qual_sample",
"title": "Amostrar documentos para validação humana",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_sample"
]
},
{
"page": "ac_qual_save_codebook",
"title": "Salvar codebook em arquivo YAML",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_save_codebook"
]
},
{
"page": "ac_qual_search_literature",
"title": "Buscar referências bibliograficas sobre um conceito via OpenAlex e LLM",
"concept": [
"qualitative"
],
"topics": [
"ac_qual_search_literature"
]
},
{
"page": "ac_readability",
"title": "Calcular legibilidade textual (Índice de Flesch adaptado ao português)",
"concept": [
"quantitative"
],
"topics": [
"ac_readability"
]
},
{
"page": "ac_sentiment",
"title": "Análise de sentimento com OpLexicon",
"concept": [
"quantitative"
],
"topics": [
"ac_sentiment"
]
},
{
"page": "ac_temporal",
"title": "Agregar uma métrica por período de tempo",
"concept": [
"quantitative"
],
"topics": [
"ac_temporal"
]
},
{
"page": "ac_tf_idf",
"title": "Calcular tf-idf para termos em documentos ou grupos",
"concept": [
"corpus"
],
"topics": [
"ac_tf_idf"
]
},
{
"page": "ac_tokenize",
"title": "Tokenizar textos de um corpus acR",
"concept": [
"corpus"
],
"topics": [
"ac_tokenize"
]
},
{
"page": "ac_top_terms",
"title": "Selecionar os termos mais frequentes",
"concept": [
"corpus"
],
"topics": [
"ac_top_terms"
]
},
{
"page": "ac_wordcloud",
"title": "Criar nuvem de palavras",
"concept": [
"visualization"
],
"topics": [
"ac_wordcloud"
]
},
{
"page": "ac_wordscores",
"title": "Escalonamento ideológico de documentos pelo método Wordscores",
"concept": [
"quantitative"
],
"topics": [
"ac_wordscores"
]
},
{
"page": "as_prompt",
"title": "Converter codebook em system prompt para LLM",
"concept": [
"qualitative"
],
"topics": [
"as_prompt",
"as_prompt.ac_codebook",
"as_prompt.default"
]
},
{
"page": "is_ac_corpus",
"title": "Verificar se um objeto é um corpus do 'acR'",
"concept": [
"corpus"
],
"topics": [
"is_ac_corpus"
]
},
{
"page": "theme_ac",
"title": "Tema visual consistente do acR",
"concept": [
"visualization"
],
"topics": [
"theme_ac"
]
}
],
"_pkglogo": "https://github.com/andersonheri/acr/raw/HEAD/man/figures/logo.png",
"_readme": "https://github.com/andersonheri/acr/raw/HEAD/README.md",
"_rundeps": [
"askpass",
"cli",
"cpp11",
"curl",
"dplyr",
"generics",
"glue",
"httr2",
"irr",
"jsonlite",
"lifecycle",
"lpSolve",
"magrittr",
"openssl",
"pillar",
"pkgconfig",
"purrr",
"R6",
"rlang",
"stringi",
"stringr",
"sys",
"tibble",
"tidyr",
"tidyselect",
"utf8",
"vctrs",
"withr",
"yaml"
],
"_vignettes": [
{
"source": "cluster.Rmd",
"filename": "cluster.html",
"title": "Agrupamento não supervisionado de documentos",
"engine": "knitr::rmarkdown",
"headings": [
"Por que agrupar documentos?",
"1. Três famílias, três leituras teóricas",
"1.1 Hard clustering (o que esta vignette faz)",
"1.2 Soft (fuzzy) clustering",
"1.3 Modelos de tópicos (LDA)",
"1.4 Como escolher?",
"2. Um corpus de dois blocos",
"3. Ajuste em três linhas",
"4. Seis formas de olhar para o mesmo cluster",
"4.1 Dendrograma: a árvore das fusões",
"4.2 Projeção PCA: a geometria do corpus",
"4.3 Mapa de calor: a assinatura da separação",
"4.4 Termos mais distintivos por cluster",
"4.5 Curva de silhueta: escolhendo k visualmente",
"4.6 Hard vs. soft: comparando com LDA",
"5. Validando contra a verdade",
"6. Escolhendo o método",
"7. E depois? Integrando com o pipeline",
"Referências"
],
"created": "2026-07-17 21:16:20",
"modified": "2026-10-15 17:52:42",
"commits": 7
},
{
"source": "qualitativo-llm.Rmd",
"filename": "qualitativo-llm.html",
"title": "Análise de Conteúdo Qualitativa com LLMs",
"engine": "knitr::rmarkdown",
"headings": [
"Visão geral",
"Por que essa ordem, e o que reportar em cada etapa",
"Quando usar LLM (e quando não usar)",
"Custo real de um estudo com LLM",
"Instalação e configuração",
"Etapa 1: Criar o codebook",
"Adicionar e remover categorias",
"Etapa 2: Enriquecer o codebook com literatura",
"Modo híbrido: definições ancoradas em referências",
"Modo literature: construção inteiramente baseada em literatura",
"Etapa 3: Fundir e traduzir codebooks",
"Fundir dois codebooks",
"Traduzir para inglês",
"Etapa 4: Inspecionar histórico e gerar system prompt",
"Etapa 5: Classificar o corpus",
"Live view: tirando o LLM do caixa-preta",
"Etapa 6: Salvar e carregar",
"Etapa 7: Validação e confiabilidade",
"Diagnosticando problemas comuns",
"1. Categorias com concordância baixa entre k_consistency",
"2. LLM devolve categoria fora do codebook",
"3. Distribuição colapsada em uma categoria",
"4. IRR humana × LLM inaceitável",
"Etapa 8: Replicabilidade e transparência",
"Referências"
],
"created": "2026-04-17 21:00:18",
"modified": "2026-10-15 17:52:42",
"commits": 22
},
{
"source": "analise-proposicoes.Rmd",
"filename": "analise-proposicoes.html",
"title": "Análise de proposições legislativas",
"engine": "knitr::rmarkdown",
"headings": [
"Contexto",
"1. Instalar e configurar",
"2. Corpus",
"3. Codebook",
"3b. Refinamento do codebook",
"Adicionar exemplos às categorias",
"Enriquecer com literatura via LLM",
"Fundir com codebook de estilo retórico",
"Gerar system prompt e inspecionar histórico",
"Salvar o codebook para replicabilidade",
"4. Classificação com LLM",
"5. Validação humana",
"6. Análise por tema e tipo",
"7. Exportar resultados",
"Referências"
],
"created": "2026-04-17 21:27:04",
"modified": "2026-10-15 17:52:42",
"commits": 13
},
{
"source": "sentimento.Rmd",
"filename": "sentimento.html",
"title": "Análise de sentimento",
"engine": "knitr::rmarkdown",
"headings": [
"O que é análise de sentimento com léxico",
"Quando usar léxico vs. LLM?",
"1. Corpus: pronunciamentos sobre uma reforma polêmica",
"2. Sentimento por documento",
"3. Comparar métodos de agregação",
"4. Visualização: barras por documento",
"5. Visualização: distribuição (densidade)",
"6. Visualização: série ordenada",
"7. Agregação por grupo (partido)",
"8. Termos-chave dentro do texto (X-ray)",
"9. Exportar para artigo/relatório",
"Referências"
],
"created": "2026-04-17 21:51:45",
"modified": "2026-10-15 19:36:11",
"commits": 15
},
{
"source": "quantitativo.Rmd",
"filename": "quantitativo.html",
"title": "Análise quantitativa de texto",
"engine": "knitr::rmarkdown",
"headings": [
"Qual métrica responde qual pergunta?",
"Sequência sugerida para reportar resultados",
"1. Construir o corpus",
"2. Limpeza: por que remover stopwords?",
"3. Tokenização",
"4. Frequência",
"5. Top termos: o vocabulário do corpus",
"6. Nuvem de palavras",
"6.1 Nuvem comparativa entre grupos",
"7. TF-IDF: o que é distintivo em cada documento?",
"8. Keyness: o que é distintivo entre grupos?",
"9. Rede de co-ocorrência",
"9.1 Trocando o peso: PMI em vez de contagem",
"9.2 Trocando o layout",
"9.3 Coocorrência como matriz (heatmap)",
"Novidades: diagnóstico de corpus, escalas e dicionários",
"10. Legibilidade e diversidade lexical",
"11. Lei de Zipf: o corpus se comporta como linguagem natural?",
"12. Concordância (KWIC) e colocações",
"12.1 KWIC: ver cada ocorrência em contexto",
"12.2 Colocações: associação estatística entre palavras",
"13. Análise temporal/diacrônica",
"14. Escalonamento Wordscores: posicionar documentos numa escala",
"15. Dicionários multi-categoria, emoções e validação",
"15.1 Dicionário multi-categoria",
"15.2 Léxico de emoções",
"15.3 Validação contra codificação humana",
"16. Análise de correspondência (CA): um mapa de grupos e termos",
"Referências"
],
"created": "2026-04-17 21:51:45",
"modified": "2026-10-15 17:52:42",
"commits": 20
},
{
"source": "llm-local-em-escala.Rmd",
"filename": "llm-local-em-escala.html",
"title": "Classificação com LLM Local em Escala",
"engine": "knitr::rmarkdown",
"headings": [
"Visão geral",
"1. Conectando a um servidor local",
"2. Dimensionando o contexto antes de gastar uma chamada",
"3. Rodando em lotes com checkpoint",
"4. Lidando com falhas técnicas",
"5. Validação humana por categoria (multilabel)",
"6. Auditando a configuração da execução",
"Referências"
],
"created": "2026-10-14 16:50:48",
"modified": "2026-10-15 17:03:31",
"commits": 4
},
{
"source": "introducao-acR.Rmd",
"filename": "introducao-acR.html",
"title": "Introdução ao acR: pipeline integrado de análise de conteúdo",
"engine": "knitr::rmarkdown",
"headings": [
"O objeto central: ac_corpus",
"1. Frequências e termos salientes",
"2. Termos distintivos com keyness",
"3. Sentimento por documento (OpLexicon)",
"4. Escolher um modelo LLM",
"5. Codificação qualitativa com LLM",
"6. Validação humana e confiabilidade",
"Próximos passos",
"Referências"
],
"created": "2026-04-17 12:47:09",
"modified": "2026-10-15 19:36:11",
"commits": 11
},
{
"source": "lda.Rmd",
"filename": "lda.html",
"title": "Modelagem de tópicos com LDA",
"engine": "knitr::rmarkdown",
"headings": [
"O que é LDA e para que serve",
"LDA vs. clustering vs. LLM",
"1. Corpus: agenda legislativa",
"2. Preparar: limpeza e remoção de stopwords",
"3. Escolher K: quantos tópicos?",
"Antes de rodar: o prior α importa em textos curtos",
"4. Treinar o modelo LDA",
"5. Termos por tópico (matriz β)",
"6. Distribuição de tópicos por documento (matriz γ)",
"7. Interpretação e nomeação dos tópicos",
"8. Visualizando as misturas: γ como heatmap",
"9. Exportar",
"Referências"
],
"created": "2026-04-17 21:51:45",
"modified": "2026-10-15 17:52:42",
"commits": 12
},
{
"source": "quickstart.Rmd",
"filename": "quickstart.html",
"title": "Quickstart: acR em 5 minutos",
"engine": "knitr::rmarkdown",
"headings": [
"1 · Um corpus mínimo",
"2 · Termos mais frequentes por grupo",
"3 · Palavras distintivas de cada lado (keyness)",
"4 · Sentimento por documento (OpLexicon PT-BR)",
"5 · Escolher um modelo LLM para a próxima etapa",
"O que vem depois?"
],
"created": "2026-07-16 20:13:45",
"modified": "2026-10-15 19:36:11",
"commits": 6
},
{
"source": "replicabilidade.Rmd",
"filename": "replicabilidade.html",
"title": "Replicabilidade ponta-a-ponta: do codebook ao relatório de método",
"engine": "knitr::rmarkdown",
"headings": [
"O pipeline em 6 etapas",
"1. Corpus",
"2. Codebook",
"3. Classificação com live view",
"4. Amostra para revisão humana",
"5. Confiabilidade inter-codificador",
"6. Relatório de método: replicabilidade automática",
"Fluxo completo em 6 linhas",
"Referências"
],
"created": "2026-07-17 00:39:28",
"modified": "2026-10-15 17:52:42",
"commits": 6
}
],
"_score": 6.698970004336019,
"_indexed": true,
"_nocasepkg": "acr",
"_universes": [
"andersonheri"
],
"_previous": "0.6.0",
"_binaries": [
{
"r": "4.7.0",
"os": "linux",
"version": "0.6.1",
"date": "2026-10-29T10:55:18.000Z",
"distro": "resolute",
"commit": "46f6bf9bfc1cfd28a828b9a4279160cfa0e26576",
"fileid": "https://r2.ropensci.org/2c1734fb604d825f658734dfe7b63c77364d90b6d3010e1e4d248954d4de2ee6",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/andersonheri/actions/runs/40859848273"
},
{
"r": "4.6.1",
"os": "linux",
"version": "0.6.1",
"date": "2026-10-29T10:55:17.000Z",
"distro": "resolute",
"commit": "46f6bf9bfc1cfd28a828b9a4279160cfa0e26576",
"fileid": "https://r2.ropensci.org/dbabdbde22c7d844eb1039e99a99cb9a9f05fc7ca6d03789f573974c5d48b0de",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/andersonheri/actions/runs/40859848273"
},
{
"r": "4.5.3",
"os": "mac",
"version": "0.6.1",
"date": "2026-10-29T11:37:45.000Z",
"commit": "46f6bf9bfc1cfd28a828b9a4279160cfa0e26576",
"fileid": "https://r2.ropensci.org/0959c35276e04c400aa774e2808216e8e40c04e672f7fd5483c683bf14f541ff",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/andersonheri/actions/runs/40859848273"
},
{
"r": "4.6.1",
"os": "mac",
"version": "0.6.1",
"date": "2026-10-29T11:42:50.000Z",
"commit": "46f6bf9bfc1cfd28a828b9a4279160cfa0e26576",
"fileid": "https://r2.ropensci.org/be31980d754ba8e03f76201e011e111cce098d32063284d819d88aea79da7da8",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/andersonheri/actions/runs/40859848273"
},
{
"r": "4.6.0",
"os": "wasm",
"version": "0.6.1",
"date": "2026-10-29T10:55:23.000Z",
"commit": "46f6bf9bfc1cfd28a828b9a4279160cfa0e26576",
"fileid": "https://r2.ropensci.org/d2ab3dd6a2e66279f32de2ea125d79c3a1a70a2d089ef865937dfd638bd5c932",
"status": "success",
"buildurl": "https://github.com/r-universe/andersonheri/actions/runs/40859848273"
},
{
"r": "4.7.0",
"os": "win",
"version": "0.6.1",
"date": "2026-10-29T10:54:08.000Z",
"commit": "46f6bf9bfc1cfd28a828b9a4279160cfa0e26576",
"fileid": "https://r2.ropensci.org/75cd416be4c2c6957a179c027bdf172e29a7be7ade48d702478444f8e6c0d1db",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/andersonheri/actions/runs/40859848273"
},
{
"r": "4.5.3",
"os": "win",
"version": "0.6.1",
"date": "2026-10-29T10:54:10.000Z",
"commit": "46f6bf9bfc1cfd28a828b9a4279160cfa0e26576",
"fileid": "https://r2.ropensci.org/5713f4f56ebb70bfdb57c22f46284a9f8c957e314a81ea8fec44035f62fe23f5",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/andersonheri/actions/runs/40859848273"
},
{
"r": "4.6.1",
"os": "win",
"version": "0.6.1",
"date": "2026-10-29T10:54:29.000Z",
"commit": "46f6bf9bfc1cfd28a828b9a4279160cfa0e26576",
"fileid": "https://r2.ropensci.org/decf8393fb5d94ec02d0c7c3fba46a292a584388b6d0434a58eb7782608c616a",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/andersonheri/actions/runs/40859848273"
}
]
}