{ "_id": "6a202b3bcd65a98ecbd0ac28", "Package": "TextAnalysisR", "Title": "A Text Mining Workflow Tool", "Version": "0.1.4", "Authors@R": "person(\"Mikyung\", \"Shin\", , \"shin.mikyung@gmail.com\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0001-7907-9193\"))", "Description": "Provides a text mining and natural language processing\nworkflow for documents. Includes preprocessing via 'quanteda',\nlexical analysis (term frequency-inverse document frequency,\nlog-odds ratios, lexical diversity) via 'tidytext', topic\nmodeling via 'stm' and the 'BERTopic' approach, semantic\nsimilarity and document clustering on transformer\nrepresentations, an interactive 'Shiny' interface with\n'ggplot2' visualization, optional 'spaCy' preprocessing, and\nlocal 'sentence-transformers' or web-based ('OpenAI', 'Gemini')\nmodel providers for retrieval-augmented generation, as\ndescribed in Shin et al. (2026)\n.", "License": "GPL (>= 3)", "Language": "en-US", "Encoding": "UTF-8", "LazyData": "true", "LazyDataCompression": "xz", "Roxygen": "list(markdown = TRUE)", "SystemRequirements": "Python (>= 3.8) with spaCy (>= 3.5) for\nlemmatization and sentence-transformers (>= 2.2) for embeddings\n(optional)", "URL": "https://mshin77.github.io/TextAnalysisR/,\nhttps://github.com/mshin77/TextAnalysisR", "BugReports": "https://github.com/mshin77/TextAnalysisR/issues", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "Config/roxygen2/version": "8.0.0", "Config/pak/sysreqs": "cmake libglpk-dev make libicu-dev libuv1-dev\nlibxml2-dev python3 zlib1g-dev", "Repository": "https://mshin77.r-universe.dev", "Date/Publication": "2026-06-03 08:32:43 UTC", "RemoteUrl": "https://github.com/mshin77/TextAnalysisR", "RemoteRef": "HEAD", "RemoteSha": "3d794248112b9e1ec1930a671f590356eef78135", "NeedsCompilation": "no", "Packaged": { "Date": "2026-06-03 13:20:10 UTC", "User": "root" }, "Author": "Mikyung Shin [aut, cre] (ORCID:\n)", "Maintainer": "Mikyung Shin ", "MD5sum": "b04d9259d5eebbb208ad1f93522ef371", "_user": "mshin77", "_type": "src", "_file": "TextAnalysisR_0.1.4.tar.gz", "_fileid": "ba419185de598da2c777dab9c628bc016913570191a2dc735e7a07ef32bbabd8", "_filesize": 3265902, "_sha256": "ba419185de598da2c777dab9c628bc016913570191a2dc735e7a07ef32bbabd8", "_created": "2026-06-03T13:20:10.000Z", "_published": "2026-06-03T13:25:15.127Z", "_distro": "noble", "_jobs": [ { "job": 79303841917, "time": 222, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7385834910" }, { "job": 79303841926, "time": 247, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7385845336" }, { "job": 79303841975, "time": 146, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7385819526" }, { "job": 79303841962, "time": 139, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7385809770" }, { "job": 79302917422, "time": 276, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7385743018" }, { "job": 79303843390, "time": 163, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7385810450" }, { "job": 79303842065, "time": 158, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7385807737" }, { "job": 79303841968, "time": 153, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7385806460" }, { "job": 79303842330, "time": 171, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7385813498" } ], "_buildurl": "https://github.com/r-universe/mshin77/actions/runs/26887243908", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/mshin77/TextAnalysisR", "_commit": { "id": "3d794248112b9e1ec1930a671f590356eef78135", "author": "Mikyung Shin ", "committer": "Mikyung Shin ", "message": "Delete rhub.yaml\n", "time": 1780475563 }, "_maintainer": { "name": "Mikyung Shin", "email": "shin.mikyung@gmail.com", "login": "mshin77", "orcid": "0000-0001-7907-9193", "twitter": "@mshin_77", "description": "Mikyung Shin, Assistant Professor of Special Education at Illinois State University", "uuid": 39714607 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.0", "role": "Depends" }, { "package": "dplyr", "role": "Imports" }, { "package": "DT", "role": "Imports" }, { "package": "ggplot2", "role": "Imports" }, { "package": "htmltools", "role": "Imports" }, { "package": "htmlwidgets", "role": "Imports" }, { "package": "igraph", "role": "Imports" }, { "package": "magrittr", "role": "Imports" }, { "package": "Matrix", "role": "Imports" }, { "package": "methods", "role": "Imports" }, { "package": "quanteda", "role": "Imports" }, { "package": "quanteda.textstats", "role": "Imports" }, { "package": "RColorBrewer", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "scales", "role": "Imports" }, { "package": "shiny", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "tidyr", "role": "Imports" }, { "package": "tidytext", "role": "Imports" }, { "package": "widyr", "role": "Imports" }, { "package": "withr", "role": "Imports" }, { "package": "aricode", "role": "Suggests" }, { "package": "tidylo", "role": "Suggests" }, { "package": "broom", "role": "Suggests" }, { "package": "patchwork", "role": "Suggests" }, { "package": "cluster", "role": "Suggests" }, { "package": "clusterCrit", "role": "Suggests" }, { "package": "colourpicker", "role": "Suggests" }, { "package": "covr", "role": "Suggests" }, { "package": "dbscan", "role": "Suggests" }, { "package": "digest", "role": "Suggests" }, { "package": "httr", "role": "Suggests" }, { "package": "jsonlite", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "markdown", "role": "Suggests" }, { "package": "MASS", "role": "Suggests" }, { "package": "moments", "role": "Suggests" }, { "package": "numform", "role": "Suggests" }, { "package": "officer", "role": "Suggests" }, { "package": "openxlsx", "role": "Suggests" }, { "package": "pdftools", "role": "Suggests" }, { "package": "progress", "role": "Suggests" }, { "package": "proxy", "role": "Suggests" }, { "package": "pscl", "role": "Suggests" }, { "package": "purrr", "role": "Suggests" }, { "package": "readxl", "role": "Suggests" }, { "package": "reticulate", "version": ">= 1.28", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "roxygen2", "role": "Suggests" }, { "package": "Rtsne", "role": "Suggests" }, { "package": "shinyBS", "role": "Suggests" }, { "package": "shinybusy", "role": "Suggests" }, { "package": "shinyjs", "role": "Suggests" }, { "package": "spelling", "role": "Suggests" }, { "package": "stm", "role": "Suggests" }, { "package": "stopwords", "role": "Suggests" }, { "package": "stringr", "role": "Suggests" }, { "package": "syuzhet", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "textdata", "role": "Suggests" }, { "package": "umap", "role": "Suggests" }, { "package": "plotly", "role": "Suggests" } ], "_owner": "mshin77", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-48", "n": 20 }, { "week": "2025-52", "n": 11 }, { "week": "2026-01", "n": 5 }, { "week": "2026-05", "n": 24 }, { "week": "2026-06", "n": 5 }, { "week": "2026-07", "n": 1 }, { "week": "2026-09", "n": 1 }, { "week": "2026-11", "n": 1 }, { "week": "2026-15", "n": 2 }, { "week": "2026-16", "n": 40 }, { "week": "2026-17", "n": 2 }, { "week": "2026-20", "n": 22 }, { "week": "2026-21", "n": 10 }, { "week": "2026-22", "n": 18 }, { "week": "2026-23", "n": 8 } ], "_tags": [], "_topics": [ "bert-model", "lexicon", "ollama", "python", "semantic", "text-mining", "topic-modeling", "word-networks" ], "_stars": 1, "_contributors": [ { "user": "mshin77", "count": 263, "uuid": 39714607 } ], "_userbio": { "uuid": 39714607, "type": "user", "name": "Mikyung Shin", "description": "Mikyung Shin, Assistant Professor of Special Education at Illinois State University" }, "_downloads": { "count": 0, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/TextAnalysisR" }, "_devurl": "https://github.com/mshin77/textanalysisr", "_pkgdown": "https://mshin77.github.io/TextAnalysisR/", "_searchresults": 34, "_rbuild": "4.6.0", "_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/TextAnalysisR.html", "manual.pdf" ], "_cranurl": false, "_exports": [ "%>%", "analyze_document_clustering", "analyze_semantic_evolution", "analyze_sentiment", "analyze_sentiment_llm", "analyze_similarity_gaps", "assess_embedding_stability", "auto_tune_embedding_topics", "calculate_assignment_consistency", "calculate_clustering_metrics", "calculate_cosine_similarity", "calculate_cross_similarity", "calculate_dispersion_metrics", "calculate_document_similarity", "calculate_keyword_stability", "calculate_lexical_dispersion", "calculate_log_odds_ratio", "calculate_semantic_drift", "calculate_similarity_robust", "calculate_text_readability", "calculate_topic_probability", "calculate_topic_stability", "calculate_weighted_log_odds", "calculate_word_frequency", "call_llm_api", "check_python_env", "check_vision_models", "clear_lexdiv_cache", "cluster_embeddings", "describe_image", "detect_multi_words", "detect_pdf_content_type", "detect_pdf_content_type_py", "export_document_clustering", "extract_cross_category_similarities", "extract_keywords_keyness", "extract_keywords_tfidf", "extract_morphology", "extract_named_entities", "extract_noun_chunks", "extract_pos_tags", "extract_subjects_objects", "extract_tables_from_pdf_py", "extract_topic_terms_df", "find_optimal_k", "find_similar_words", "find_topic_matches", "fit_embedding_model", "fit_embedding_topics", "fit_semantic_model", "fit_temporal_model", "fit_topic_prevalence_model", "generate_cluster_labels", "generate_cluster_labels_auto", "generate_embeddings", "generate_topic_content", "generate_topic_labels", "get_available_dfm", "get_available_tokens", "get_best_embeddings", "get_content_type_prompt", "get_content_type_user_template", "get_sentences", "get_sentiment_color", "get_sentiment_colors", "get_spacy_model_info", "get_topic_prevalence", "get_topic_terms", "get_topic_texts", "get_word_similarity", "identify_topic_trends", "import_files", "init_spacy_nlp", "lemmatize_tokens", "lexical_diversity_analysis", "lexical_frequency_analysis", "plot_cluster_terms", "plot_cross_category_heatmap", "plot_document_sentiment_trajectory", "plot_emotion_radar", "plot_entity_frequencies", "plot_keyness_keywords", "plot_keyword_comparison", "plot_lexical_dispersion", "plot_lexical_diversity_distribution", "plot_log_odds_ratio", "plot_model_comparison", "plot_morphology_feature", "plot_mwe_frequency", "plot_ngram_frequency", "plot_pos_frequencies", "plot_quality_metrics", "plot_readability_by_group", "plot_readability_distribution", "plot_semantic_viz", "plot_sentiment_boxplot", "plot_sentiment_by_category", "plot_sentiment_distribution", "plot_sentiment_violin", "plot_similarity_heatmap", "plot_term_trends_continuous", "plot_tfidf_keywords", "plot_top_readability_documents", "plot_topic_effects_categorical", "plot_topic_effects_continuous", "plot_topic_probability", "plot_weighted_log_odds", "plot_word_frequency", "plot_word_probability", "prep_texts", "process_pdf_unified", "reduce_dimensions", "render_displacy_dep", "render_displacy_ent", "run_app", "run_neural_topics_internal", "run_rag_search", "run_text_workflow", "semantic_document_clustering", "semantic_similarity_analysis", "sentiment_embedding_analysis", "sentiment_lexicon_analysis", "setup_python_env", "show_web_banner", "spacy_extract_entities", "spacy_has_vectors", "spacy_initialized", "spacy_lemmatize", "spacy_parse_full", "summarize_morphology", "unite_cols", "validate_cross_models", "validate_semantic_coherence", "word_co_occurrence_network", "word_correlation_network" ], "_datasets": [ { "name": "acronym", "title": "Acronym List", "object": "acronym", "class": [ "spec_tbl_df", "tbl_df", "tbl", "data.frame" ], "fields": [ "3D", "three-dimensional" ], "rows": 145, "table": true, "tojson": true }, { "name": "SpecialEduTech", "title": "Special education technology bibliographic data", "object": "SpecialEduTech", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "reference_type", "author", "year", "title", "keyword", "abstract" ], "rows": 490, "table": true, "tojson": true }, { "name": "stm_15", "title": "An example structure of a structural topic model", "object": "stm_15", "class": [ "STM" ], "fields": [], "table": false, "tojson": false }, { "name": "stopwords_list", "title": "Stopwords List", "object": "stopwords_list", "class": [ "character" ], "fields": [], "table": false, "tojson": true } ], "_help": [ { "page": "acronym", "title": "Acronym List", "topics": [ "acronym" ] }, { "page": "analyze_document_clustering", "title": "Analyze Document Clustering", "concept": [ "semantic" ], "topics": [ "analyze_document_clustering" ] }, { "page": "analyze_semantic_evolution", "title": "Analyze Semantic Evolution", "concept": [ "topic-modeling" ], "topics": [ "analyze_semantic_evolution" ] }, { "page": "analyze_sentiment", "title": "Analyze Text Sentiment", "concept": [ "sentiment" ], "topics": [ "analyze_sentiment" ] }, { "page": "analyze_sentiment_llm", "title": "LLM-based Sentiment Analysis", "concept": [ "sentiment" ], "topics": [ "analyze_sentiment_llm" ] }, { "page": "analyze_similarity_gaps", "title": "Analyze Similarity Gaps Between Categories", "concept": [ "semantic" ], "topics": [ "analyze_similarity_gaps" ] }, { "page": "assess_embedding_stability", "title": "Assess Embedding Topic Model Stability", "concept": [ "topic-modeling" ], "topics": [ "assess_embedding_stability" ] }, { "page": "auto_tune_embedding_topics", "title": "Auto-tune BERTopic Hyperparameters", "concept": [ "topic-modeling" ], "topics": [ "auto_tune_embedding_topics" ] }, { "page": "calculate_assignment_consistency", "title": "Calculate Assignment Consistency", "concept": [ "topic-modeling" ], "topics": [ "calculate_assignment_consistency" ] }, { "page": "calculate_clustering_metrics", "title": "Calculate Clustering Quality Metrics", "concept": [ "semantic" ], "topics": [ "calculate_clustering_metrics" ] }, { "page": "calculate_cross_similarity", "title": "Calculate Cross-Matrix Cosine Similarity", "concept": [ "semantic" ], "topics": [ "calculate_cross_similarity" ] }, { "page": "calculate_dispersion_metrics", "title": "Calculate Dispersion Metrics", "concept": [ "lexical" ], "topics": [ "calculate_dispersion_metrics" ] }, { "page": "calculate_keyword_stability", "title": "Calculate Keyword Stability", "concept": [ "topic-modeling" ], "topics": [ "calculate_keyword_stability" ] }, { "page": "calculate_lexical_dispersion", "title": "Calculate Lexical Dispersion", "concept": [ "lexical" ], "topics": [ "calculate_lexical_dispersion" ] }, { "page": "calculate_log_odds_ratio", "title": "Calculate Log Odds Ratio Between Categories", "concept": [ "lexical" ], "topics": [ "calculate_log_odds_ratio" ] }, { "page": "calculate_semantic_drift", "title": "Calculate Semantic Drift", "concept": [ "topic-modeling" ], "topics": [ "calculate_semantic_drift" ] }, { "page": "calculate_similarity_robust", "title": "Calculate Document Similarity with Fallbacks", "concept": [ "semantic" ], "topics": [ "calculate_similarity_robust" ] }, { "page": "calculate_text_readability", "title": "Calculate Text Readability", "concept": [ "lexical" ], "topics": [ "calculate_text_readability" ] }, { "page": "calculate_topic_probability", "title": "Calculate Topic Probabilities", "concept": [ "topic-modeling" ], "topics": [ "calculate_topic_probability" ] }, { "page": "calculate_topic_stability", "title": "Calculate Topic Stability", "concept": [ "topic-modeling" ], "topics": [ "calculate_topic_stability" ] }, { "page": "calculate_weighted_log_odds", "title": "Calculate Weighted Log Odds Ratio", "concept": [ "lexical" ], "topics": [ "calculate_weighted_log_odds" ] }, { "page": "calculate_word_frequency", "title": "Analyze and Visualize Word Frequencies Across a Continuous Variable", "topics": [ "calculate_word_frequency" ] }, { "page": "call_llm_api", "title": "Call LLM API (Unified Wrapper)", "concept": [ "ai" ], "topics": [ "call_llm_api" ] }, { "page": "clear_lexdiv_cache", "title": "Clear Lexical Diversity Cache", "concept": [ "lexical" ], "topics": [ "clear_lexdiv_cache" ] }, { "page": "cluster_embeddings", "title": "Embedding-based Document Clustering", "concept": [ "semantic" ], "topics": [ "cluster_embeddings" ] }, { "page": "describe_image", "title": "Describe Image Using Vision LLM", "concept": [ "ai" ], "topics": [ "describe_image" ] }, { "page": "detect_multi_words", "title": "Detect Multi-Word Expressions", "concept": [ "lexical" ], "topics": [ "detect_multi_words" ] }, { "page": "detect_pdf_content_type", "title": "Detect PDF Content Type", "concept": [ "pdf" ], "topics": [ "detect_pdf_content_type" ] }, { "page": "export_document_clustering", "title": "Export Document Clustering Analysis", "concept": [ "semantic" ], "topics": [ "export_document_clustering" ] }, { "page": "extract_cross_category_similarities", "title": "Extract Cross-Category Similarities from Full Similarity Matrix", "concept": [ "semantic" ], "topics": [ "extract_cross_category_similarities" ] }, { "page": "extract_keywords_keyness", "title": "Extract Keywords Using Statistical Keyness", "concept": [ "lexical" ], "topics": [ "extract_keywords_keyness" ] }, { "page": "extract_keywords_tfidf", "title": "Extract Keywords Using TF-IDF", "concept": [ "lexical" ], "topics": [ "extract_keywords_tfidf" ] }, { "page": "extract_morphology", "title": "Extract Morphological Features", "concept": [ "lexical" ], "topics": [ "extract_morphology" ] }, { "page": "extract_named_entities", "title": "Extract Named Entities from Tokens", "concept": [ "lexical" ], "topics": [ "extract_named_entities" ] }, { "page": "extract_noun_chunks", "title": "Extract Noun Chunks", "concept": [ "lexical" ], "topics": [ "extract_noun_chunks" ] }, { "page": "extract_pos_tags", "title": "Extract Part-of-Speech Tags from Tokens", "concept": [ "lexical" ], "topics": [ "extract_pos_tags" ] }, { "page": "extract_subjects_objects", "title": "Extract Subjects and Objects", "concept": [ "lexical" ], "topics": [ "extract_subjects_objects" ] }, { "page": "extract_topic_terms_df", "title": "Build a topic-term data frame from any supported topic model", "concept": [ "topic-modeling" ], "topics": [ "extract_topic_terms_df" ] }, { "page": "find_optimal_k", "title": "Find Optimal Number of Topics", "concept": [ "topic-modeling" ], "topics": [ "find_optimal_k" ] }, { "page": "find_similar_words", "title": "Find Similar Words", "concept": [ "lexical" ], "topics": [ "find_similar_words" ] }, { "page": "find_topic_matches", "title": "Find Similar Topics", "concept": [ "topic-modeling" ], "topics": [ "find_topic_matches" ] }, { "page": "fit_embedding_model", "title": "Fit Embedding-based Topic Model", "concept": [ "topic-modeling" ], "topics": [ "fit_embedding_model" ] }, { "page": "fit_semantic_model", "title": "Fit Semantic Model", "concept": [ "semantic" ], "topics": [ "fit_semantic_model" ] }, { "page": "fit_temporal_model", "title": "Fit Temporal Topic Model", "concept": [ "topic-modeling" ], "topics": [ "fit_temporal_model" ] }, { "page": "fit_topic_prevalence_model", "title": "Fit Topic Prevalence Model", "concept": [ "topic-modeling" ], "topics": [ "fit_topic_prevalence_model" ] }, { "page": "generate_cluster_labels", "title": "Generate Cluster Label Suggestions (Human-in-the-Loop)", "concept": [ "semantic" ], "topics": [ "generate_cluster_labels" ] }, { "page": "generate_cluster_labels_auto", "title": "Generate Cluster Labels", "concept": [ "semantic" ], "topics": [ "generate_cluster_labels_auto" ] }, { "page": "generate_embeddings", "title": "Generate Embeddings", "concept": [ "semantic" ], "topics": [ "generate_embeddings" ] }, { "page": "generate_topic_content", "title": "Generate Content from Topic Terms", "concept": [ "ai" ], "topics": [ "generate_topic_content" ] }, { "page": "generate_topic_labels", "title": "Generate Topic Labels Using AI", "concept": [ "topic-modeling" ], "topics": [ "generate_topic_labels" ] }, { "page": "get_best_embeddings", "title": "Get Best Available Embeddings", "concept": [ "ai" ], "topics": [ "get_best_embeddings" ] }, { "page": "get_content_type_prompt", "title": "Get Default System Prompt for Content Type", "concept": [ "ai" ], "topics": [ "get_content_type_prompt" ] }, { "page": "get_content_type_user_template", "title": "Get Default User Prompt Template for Content Type", "concept": [ "ai" ], "topics": [ "get_content_type_user_template" ] }, { "page": "get_sentences", "title": "Get Sentences", "concept": [ "lexical" ], "topics": [ "get_sentences" ] }, { "page": "get_spacy_model_info", "title": "Get spaCy Model Information", "concept": [ "lexical" ], "topics": [ "get_spacy_model_info" ] }, { "page": "get_topic_prevalence", "title": "Get Topic Prevalence (Gamma) from STM Model", "concept": [ "topic-modeling" ], "topics": [ "get_topic_prevalence" ] }, { "page": "get_topic_terms", "title": "Select Top Terms for Each Topic", "concept": [ "topic-modeling" ], "topics": [ "get_topic_terms" ] }, { "page": "get_topic_texts", "title": "Convert Topic Terms to Text Strings", "concept": [ "topic-modeling" ], "topics": [ "get_topic_texts" ] }, { "page": "get_word_similarity", "title": "Calculate Word Similarity", "concept": [ "lexical" ], "topics": [ "get_word_similarity" ] }, { "page": "identify_topic_trends", "title": "Identify Topic Trends", "concept": [ "topic-modeling" ], "topics": [ "identify_topic_trends" ] }, { "page": "import_files", "title": "Process Files", "concept": [ "preprocessing" ], "topics": [ "import_files" ] }, { "page": "lemmatize_tokens", "title": "Lemmatize Tokens with Batch Processing", "concept": [ "preprocessing" ], "topics": [ "lemmatize_tokens" ] }, { "page": "lexical_analysis", "title": "Lexical Analysis Functions", "concept": [ "lexical" ], "topics": [ "lexical_analysis" ] }, { "page": "lexical_diversity_analysis", "title": "Lexical Diversity Analysis", "concept": [ "lexical" ], "topics": [ "lexical_diversity_analysis" ] }, { "page": "lexical_frequency_analysis", "title": "Lexical Frequency Analysis", "concept": [ "lexical" ], "topics": [ "lexical_frequency_analysis" ] }, { "page": "plot_cluster_terms", "title": "Plot Cluster Top Terms", "concept": [ "visualization" ], "topics": [ "plot_cluster_terms" ] }, { "page": "plot_cross_category_heatmap", "title": "Plot Cross-Category Similarity Comparison", "concept": [ "visualization" ], "topics": [ "plot_cross_category_heatmap" ] }, { "page": "plot_document_sentiment_trajectory", "title": "Plot Document Sentiment Trajectory", "concept": [ "sentiment" ], "topics": [ "plot_document_sentiment_trajectory" ] }, { "page": "plot_emotion_radar", "title": "Plot Emotion Radar Chart", "concept": [ "sentiment" ], "topics": [ "plot_emotion_radar" ] }, { "page": "plot_entity_frequencies", "title": "Plot Named Entity Frequencies", "concept": [ "visualization" ], "topics": [ "plot_entity_frequencies" ] }, { "page": "plot_keyness_keywords", "title": "Plot Statistical Keyness", "concept": [ "lexical" ], "topics": [ "plot_keyness_keywords" ] }, { "page": "plot_keyword_comparison", "title": "Plot Keyword Comparison (TF-IDF vs Frequency)", "concept": [ "lexical" ], "topics": [ "plot_keyword_comparison" ] }, { "page": "plot_lexical_dispersion", "title": "Plot Lexical Dispersion", "concept": [ "visualization" ], "topics": [ "plot_lexical_dispersion" ] }, { "page": "plot_lexical_diversity_distribution", "title": "Plot Lexical Diversity Distribution", "concept": [ "lexical" ], "topics": [ "plot_lexical_diversity_distribution" ] }, { "page": "plot_log_odds_ratio", "title": "Plot Log Odds Ratio", "concept": [ "visualization" ], "topics": [ "plot_log_odds_ratio" ] }, { "page": "plot_model_comparison", "title": "Plot Topic Model Comparison Scatter", "concept": [ "topic-modeling" ], "topics": [ "plot_model_comparison" ] }, { "page": "plot_morphology_feature", "title": "Plot Morphology Feature Distribution", "concept": [ "lexical" ], "topics": [ "plot_morphology_feature" ] }, { "page": "plot_mwe_frequency", "title": "Plot Multi-Word Expression Frequency", "concept": [ "visualization" ], "topics": [ "plot_mwe_frequency" ] }, { "page": "plot_ngram_frequency", "title": "Plot N-gram Frequency", "concept": [ "visualization" ], "topics": [ "plot_ngram_frequency" ] }, { "page": "plot_pos_frequencies", "title": "Plot Part-of-Speech Tag Frequencies", "concept": [ "visualization" ], "topics": [ "plot_pos_frequencies" ] }, { "page": "plot_quality_metrics", "title": "Plot Topic Model Quality Metrics", "concept": [ "topic-modeling" ], "topics": [ "plot_quality_metrics" ] }, { "page": "plot_readability_by_group", "title": "Plot Readability by Group", "concept": [ "lexical" ], "topics": [ "plot_readability_by_group" ] }, { "page": "plot_readability_distribution", "title": "Plot Readability Distribution", "concept": [ "lexical" ], "topics": [ "plot_readability_distribution" ] }, { "page": "plot_semantic_viz", "title": "Plot Semantic Analysis Visualization", "concept": [ "visualization" ], "topics": [ "plot_semantic_viz" ] }, { "page": "plot_sentiment_boxplot", "title": "Plot Sentiment Box Plot by Category", "concept": [ "sentiment" ], "topics": [ "plot_sentiment_boxplot" ] }, { "page": "plot_sentiment_by_category", "title": "Plot Sentiment by Category", "concept": [ "sentiment" ], "topics": [ "plot_sentiment_by_category" ] }, { "page": "plot_sentiment_distribution", "title": "Plot Sentiment Distribution", "concept": [ "sentiment" ], "topics": [ "plot_sentiment_distribution" ] }, { "page": "plot_sentiment_violin", "title": "Plot Sentiment Violin Plot by Category", "concept": [ "sentiment" ], "topics": [ "plot_sentiment_violin" ] }, { "page": "plot_similarity_heatmap", "title": "Plot Document Similarity Heatmap", "concept": [ "visualization" ], "topics": [ "plot_similarity_heatmap" ] }, { "page": "plot_term_trends_continuous", "title": "Plot Term Frequency Trends by Continuous Variable", "concept": [ "visualization" ], "topics": [ "plot_term_trends_continuous" ] }, { "page": "plot_tfidf_keywords", "title": "Plot TF-IDF Keywords", "concept": [ "lexical" ], "topics": [ "plot_tfidf_keywords" ] }, { "page": "plot_top_readability_documents", "title": "Plot Top Documents by Readability", "concept": [ "lexical" ], "topics": [ "plot_top_readability_documents" ] }, { "page": "plot_topic_effects_categorical", "title": "Plot Topic Effects for Categorical Variables", "concept": [ "topic-modeling" ], "topics": [ "plot_topic_effects_categorical" ] }, { "page": "plot_topic_effects_continuous", "title": "Plot Topic Effects for Continuous Variables", "concept": [ "topic-modeling" ], "topics": [ "plot_topic_effects_continuous" ] }, { "page": "plot_topic_probability", "title": "Plot Per-Document Per-Topic Probabilities", "concept": [ "topic-modeling" ], "topics": [ "plot_topic_probability" ] }, { "page": "plot_weighted_log_odds", "title": "Plot Weighted Log Odds", "concept": [ "visualization" ], "topics": [ "plot_weighted_log_odds" ] }, { "page": "plot_word_frequency", "title": "Plot Word Frequency", "concept": [ "visualization" ], "topics": [ "plot_word_frequency" ] }, { "page": "plot_word_probability", "title": "Plot Word Probabilities by Topic", "concept": [ "topic-modeling" ], "topics": [ "plot_word_probability" ] }, { "page": "prep_texts", "title": "Preprocess Text Data", "concept": [ "preprocessing" ], "topics": [ "prep_texts" ] }, { "page": "process_pdf_unified", "title": "Process PDF File (Unified Entry Point)", "concept": [ "preprocessing" ], "topics": [ "process_pdf_unified" ] }, { "page": "reduce_dimensions", "title": "Dimensionality Reduction Analysis", "concept": [ "semantic" ], "topics": [ "reduce_dimensions" ] }, { "page": "render_displacy_dep", "title": "Render displaCy Dependency Visualization", "concept": [ "lexical" ], "topics": [ "render_displacy_dep" ] }, { "page": "render_displacy_ent", "title": "Render displaCy Entity Visualization", "concept": [ "lexical" ], "topics": [ "render_displacy_ent" ] }, { "page": "run_app", "title": "Launch the TextAnalysisR app", "topics": [ "run_app" ] }, { "page": "run_rag_search", "title": "RAG Semantic Search", "concept": [ "ai" ], "topics": [ "run_rag_search" ] }, { "page": "run_text_workflow", "title": "Complete Text Mining Workflow", "topics": [ "run_text_workflow" ] }, { "page": "semantic_document_clustering", "title": "Semantic Document Clustering", "concept": [ "semantic" ], "topics": [ "semantic_document_clustering" ] }, { "page": "semantic_similarity_analysis", "title": "Semantic Similarity Analysis", "concept": [ "semantic" ], "topics": [ "semantic_similarity_analysis" ] }, { "page": "sentiment_embedding_analysis", "title": "Embedding-based Sentiment Analysis", "concept": [ "sentiment" ], "topics": [ "sentiment_embedding_analysis" ] }, { "page": "sentiment_lexicon_analysis", "title": "Analyze Sentiment Using Tidytext Lexicons", "concept": [ "sentiment" ], "topics": [ "sentiment_lexicon_analysis" ] }, { "page": "setup_python_env", "title": "Setup Python Environment", "topics": [ "setup_python_env" ] }, { "page": "spacy_extract_entities", "title": "Extract Named Entities with spaCy", "concept": [ "lexical" ], "topics": [ "spacy_extract_entities" ] }, { "page": "spacy_has_vectors", "title": "Check if Model Has Word Vectors", "concept": [ "lexical" ], "topics": [ "spacy_has_vectors" ] }, { "page": "spacy_initialized", "title": "Check if spaCy is Initialized", "concept": [ "lexical" ], "topics": [ "spacy_initialized" ] }, { "page": "spacy_lemmatize", "title": "Lemmatize Texts with spaCy", "concept": [ "lexical" ], "topics": [ "spacy_lemmatize" ] }, { "page": "spacy_parse_full", "title": "Parse Texts with spaCy", "concept": [ "lexical" ], "topics": [ "spacy_parse_full" ] }, { "page": "SpecialEduTech", "title": "Special education technology bibliographic data", "topics": [ "SpecialEduTech" ] }, { "page": "stm_15", "title": "An example structure of a structural topic model", "topics": [ "stm_15" ] }, { "page": "stopwords_list", "title": "Stopwords List", "topics": [ "stopwords_list" ] }, { "page": "summarize_morphology", "title": "Summarize Morphology Features", "concept": [ "lexical" ], "topics": [ "summarize_morphology" ] }, { "page": "unite_cols", "title": "Unite Text Columns", "concept": [ "preprocessing" ], "topics": [ "unite_cols" ] }, { "page": "validate_cross_models", "title": "Cross-Analysis Validation", "concept": [ "semantic" ], "topics": [ "validate_cross_models" ] }, { "page": "validate_semantic_coherence", "title": "Validate Semantic Coherence", "concept": [ "topic-modeling" ], "topics": [ "validate_semantic_coherence" ] }, { "page": "word_co_occurrence_network", "title": "Analyze and Visualize Word Co-occurrence Networks", "concept": [ "semantic" ], "topics": [ "word_co_occurrence_network" ] }, { "page": "word_correlation_network", "title": "Analyze and Visualize Word Correlation Networks", "concept": [ "semantic" ], "topics": [ "word_correlation_network" ] } ], "_pkglogo": "https://github.com/mshin77/TextAnalysisR/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/mshin77/TextAnalysisR/raw/HEAD/README.md", "_rundeps": [ "backports", "base64enc", "broom", "bslib", "cachem", "cli", "commonmark", "cpp11", "crosstalk", "digest", "dplyr", "DT", "evaluate", "farver", "fastmap", "fastmatch", "fontawesome", "fs", "generics", "ggplot2", "glue", "gtable", "highr", "htmltools", "htmlwidgets", "httpuv", "igraph", "isoband", "ISOcodes", "janeaustenr", "jquerylib", "jsonlite", "knitr", "labeling", "later", "lattice", "lazyeval", "lifecycle", "magrittr", "Matrix", "memoise", "mime", "nsyllable", "otel", "pillar", "pkgconfig", "plyr", "promises", "proxyC", "purrr", "quanteda", "quanteda.textstats", "R6", "rappdirs", "RColorBrewer", "Rcpp", "RcppArmadillo", "reshape2", "rlang", "rmarkdown", "S7", "sass", "scales", "shiny", "SnowballC", "sourcetools", "stopwords", "stringi", "stringr", "tibble", "tidyr", "tidyselect", "tidytext", "tinytex", "tokenizers", "utf8", "vctrs", "viridisLite", "widyr", "withr", "xfun", "xml2", "xtable", "yaml" ], "_vignettes": [ { "source": "web_accessibility.Rmd", "filename": "web_accessibility.html", "title": "Accessibility", "engine": "knitr::rmarkdown", "headings": [ "Keyboard Navigation", "Visual Features", "Screen Reader Support", "Language Support" ], "created": "2025-11-30 05:11:05", "modified": "2026-06-02 00:35:57", "commits": 6 }, { "source": "ai_integration.Rmd", "filename": "ai_integration.html", "title": "AI Integration", "engine": "knitr::rmarkdown", "headings": [ "Providers", "Setup", "Default Models", "Responsible AI Design" ], "created": "2025-12-29 07:02:19", "modified": "2026-06-02 00:35:57", "commits": 12 }, { "source": "quickstart.Rmd", "filename": "quickstart.html", "title": "Getting Started", "engine": "knitr::rmarkdown", "headings": [ "Install", "Launch App", "Quick Example", "Features" ], "created": "2025-11-30 05:11:05", "modified": "2026-05-27 14:28:54", "commits": 6 }, { "source": "installation.Rmd", "filename": "installation.html", "title": "Installation", "engine": "knitr::rmarkdown", "headings": [ "R Package", "Web App", "Optional Features", "Linguistic Analysis (spaCy)", "Python Features", "Troubleshooting" ], "created": "2025-11-30 05:11:05", "modified": "2026-06-02 00:35:57", "commits": 9 }, { "source": "lexical_analysis.Rmd", "filename": "lexical_analysis.html", "title": "Lexical Analysis", "engine": "knitr::rmarkdown", "headings": [ "Setup", "Linguistic Annotation", "Part-of-Speech Tags", "Morphological Features", "Named Entity Recognition", "Frequency Trends", "Keywords", "TF-IDF", "Statistical Keyness", "Comparison", "Lexical Diversity", "Readability", "Log Odds Ratio", "Lexical Dispersion", "Multi-Word Expressions" ], "created": "2025-11-30 05:11:05", "modified": "2026-06-02 00:35:57", "commits": 12 }, { "source": "multimodal_analysis.Rmd", "filename": "multimodal_analysis.html", "title": "Multimodal Analysis", "engine": "knitr::rmarkdown", "headings": [ "How It Works", "Functions", "Provider Comparison" ], "created": "2025-11-30 05:11:05", "modified": "2026-06-02 00:35:57", "commits": 9 }, { "source": "preprocessing.Rmd", "filename": "preprocessing.html", "title": "Preprocessing", "engine": "knitr::rmarkdown", "headings": [ "Workflow", "Multi-word Expressions" ], "created": "2025-11-30 05:11:05", "modified": "2026-05-28 12:19:25", "commits": 8 }, { "source": "python_environment.Rmd", "filename": "python_environment.html", "title": "Python Environment", "engine": "knitr::rmarkdown", "headings": [ "Quick Setup", "Check Status", "Common Issues", "\"Another Python already initialized\"", "Environment in OneDrive", "spaCy Models", "Deep Learning (Optional)", "Diagnostics" ], "created": "2025-11-30 05:11:05", "modified": "2026-06-02 00:35:57", "commits": 9 }, { "source": "cybersecurity.Rmd", "filename": "cybersecurity.html", "title": "Security", "engine": "knitr::rmarkdown", "headings": [ "Input Validation", "API Key Security", "Network Security", "Data Protection", "Infrastructure" ], "created": "2025-11-30 05:11:05", "modified": "2026-06-02 00:35:57", "commits": 6 }, { "source": "semantic_analysis.Rmd", "filename": "semantic_analysis.html", "title": "Semantic Analysis", "engine": "knitr::rmarkdown", "headings": [ "Setup", "Word Co-occurrence", "Word Correlation", "Document Similarity", "Comparative Analysis", "Semantic Search", "Sentiment & Emotion", "Document Groups" ], "created": "2025-11-30 05:11:05", "modified": "2026-06-03 02:14:00", "commits": 20 }, { "source": "topic_modeling.Rmd", "filename": "topic_modeling.html", "title": "Topic Modeling", "engine": "knitr::rmarkdown", "headings": [ "Setup", "Model Configuration", "Word-Topic", "Content Generation", "Document-Topic", "Quotes", "Estimated Effects", "Categorical Covariates", "Continuous Covariates", "Embedding-based Topics", "STM vs Embedding" ], "created": "2025-11-30 05:11:05", "modified": "2026-06-02 00:35:57", "commits": 17 } ], "_score": 5.44793286559218, "_indexed": true, "_nocasepkg": "textanalysisr", "_universes": [ "mshin77" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.4", "date": "2026-06-03T13:23:17.000Z", "distro": "noble", "commit": "3d794248112b9e1ec1930a671f590356eef78135", "fileid": "89f57fdf112e3d28c1166c9139add0ae4caf18db3fe595695820ed7a967eec3b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mshin77/actions/runs/26887243908" }, { "r": "4.6.0", "os": "linux", "version": "0.1.4", "date": "2026-06-03T13:23:45.000Z", "distro": "noble", "commit": "3d794248112b9e1ec1930a671f590356eef78135", "fileid": "6f1387315e1e6c48514e9ed67a760914b62ea98d6ddc463268c67b1b49dea51f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mshin77/actions/runs/26887243908" }, { "r": "4.5.3", "os": "mac", "version": "0.1.4", "date": "2026-06-03T13:23:01.000Z", "commit": "3d794248112b9e1ec1930a671f590356eef78135", "fileid": "57e5a629c47b646c5b16df406f45b35172c0137526e471618dcdbf77cb85b781", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mshin77/actions/runs/26887243908" }, { "r": "4.6.0", "os": "mac", "version": "0.1.4", "date": "2026-06-03T13:22:32.000Z", "commit": "3d794248112b9e1ec1930a671f590356eef78135", "fileid": "ceca15824efbe946cf3ea9c8045609f7529b7cb4f92dafb9c831b8f03f4fa1ff", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mshin77/actions/runs/26887243908" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.4", "date": "2026-06-03T13:23:25.000Z", "commit": "3d794248112b9e1ec1930a671f590356eef78135", "fileid": "e63a23653963f926743c7a2dcaa883c1b41c2c1af3e57fcc71242e5a9129f68c", "status": "success", "buildurl": "https://github.com/r-universe/mshin77/actions/runs/26887243908" }, { "r": "4.7.0", "os": "win", "version": "0.1.4", "date": "2026-06-03T13:21:56.000Z", "commit": "3d794248112b9e1ec1930a671f590356eef78135", "fileid": "619fe851d0811ebb62e430848e033ff1bdf91e6d39eac0edd5d5013601cfebcf", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mshin77/actions/runs/26887243908" }, { "r": "4.5.3", "os": "win", "version": "0.1.4", "date": "2026-06-03T13:21:56.000Z", "commit": "3d794248112b9e1ec1930a671f590356eef78135", "fileid": "f0d7f8bbc6a3b6ca84774af26818f60310d0225fe75119140dd65587c0ebae74", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mshin77/actions/runs/26887243908" }, { "r": "4.6.0", "os": "win", "version": "0.1.4", "date": "2026-06-03T13:22:10.000Z", "commit": "3d794248112b9e1ec1930a671f590356eef78135", "fileid": "921a770081c70ed71b3993d42da5b7f21419a41d931ef5072db4a55c49f8d0f4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mshin77/actions/runs/26887243908" } ] }