Package index • TextAnalysisR

Getting Started

Launch the app and import data

run_app(): Launch the TextAnalysisR app
import_files(): Process Files

Preprocessing

Text preparation and feature extraction

unite_cols(): Unite Text Columns
prep_texts(): Preprocess Text Data
detect_multi_words(): Detect Multi-Word Expressions
get_available_dfm(): Get Available Document-Feature Matrix with Fallback
get_available_tokens(): Get Available Tokens with Fallback

Linguistic Analysis

POS tagging, NER, and morphology (requires Python)

extract_pos_tags(): Extract Part-of-Speech Tags from Tokens
extract_named_entities(): Extract Named Entities from Tokens
extract_morphology(): Extract Morphological Features
summarize_morphology(): Summarize Morphology Features
plot_pos_frequencies(): Plot Part-of-Speech Tag Frequencies
plot_entity_frequencies(): Plot Named Entity Frequencies
plot_morphology_feature(): Plot Morphology Feature Distribution
render_displacy_ent(): Render displaCy Entity Visualization

Lexical Analysis

Word frequency, keywords, readability, and dispersion

calculate_word_frequency(): Analyze and Visualize Word Frequencies Across a Continuous Variable
lexical_analysis: Lexical Analysis Functions
extract_keywords_keyness(): Extract Keywords Using Statistical Keyness
extract_keywords_tfidf(): Extract Keywords Using TF-IDF
lexical_frequency_analysis(): Lexical Frequency Analysis
lexical_diversity_analysis(): Lexical Diversity Analysis
clear_lexdiv_cache(): Clear Lexical Diversity Cache
calculate_text_readability(): Calculate Text Readability
calculate_log_odds_ratio(): Calculate Log Odds Ratio Between Categories
calculate_weighted_log_odds(): Calculate Weighted Log Odds Ratio
calculate_lexical_dispersion(): Calculate Lexical Dispersion
calculate_dispersion_metrics(): Calculate Dispersion Metrics
plot_word_frequency(): Plot Word Frequency
plot_tfidf_keywords(): Plot TF-IDF Keywords
plot_keyness_keywords(): Plot Statistical Keyness
plot_keyword_comparison(): Plot Keyword Comparison (TF-IDF vs Frequency)
plot_ngram_frequency(): Plot N-gram Frequency
plot_mwe_frequency(): Plot Multi-Word Expression Frequency
plot_readability_distribution(): Plot Readability Distribution
plot_readability_by_group(): Plot Readability by Group
plot_top_readability_documents(): Plot Top Documents by Readability
plot_lexical_diversity_distribution(): Plot Lexical Diversity Distribution
plot_log_odds_ratio(): Plot Log Odds Ratio
plot_weighted_log_odds(): Plot Weighted Log Odds
plot_lexical_dispersion(): Plot Lexical Dispersion

Sentiment Analysis

Lexicon and embedding-based sentiment

analyze_sentiment(): Analyze Text Sentiment
sentiment_lexicon_analysis(): Analyze Sentiment Using Tidytext Lexicons
sentiment_embedding_analysis(): Embedding-based Sentiment Analysis
plot_sentiment_boxplot(): Plot Sentiment Box Plot by Category
plot_sentiment_by_category(): Plot Sentiment by Category
plot_sentiment_distribution(): Plot Sentiment Distribution
plot_sentiment_violin(): Plot Sentiment Violin Plot by Category
plot_emotion_radar(): Plot Emotion Radar Chart
plot_document_sentiment_trajectory(): Plot Document Sentiment Trajectory
get_sentiment_color(): Generate Sentiment Color Gradient
get_sentiment_colors(): Get Sentiment Color Palette

Semantic Analysis

Similarity, clustering, and networks

generate_embeddings(): Generate Embeddings
reduce_dimensions(): Dimensionality Reduction Analysis
calculate_document_similarity(): Calculate Document Similarity
calculate_similarity_robust(): Calculate Similarity Robust
calculate_cosine_similarity(): Calculate Cosine Similarity Matrix
semantic_similarity_analysis(): Semantic Similarity Analysis
semantic_document_clustering(): Semantic Document Clustering
cluster_embeddings(): Embedding-based Document Clustering
analyze_document_clustering(): Analyze Document Clustering
export_document_clustering(): Export Document Clustering Analysis
generate_cluster_labels(): Generate Cluster Label Suggestions (Human-in-the-Loop)
generate_cluster_labels_auto(): Generate Cluster Labels
temporal_semantic_analysis(): Temporal Semantic Analysis
analyze_semantic_evolution(): Analyze Semantic Evolution
word_co_occurrence_network(): Analyze and Visualize Word Co-occurrence Networks
word_correlation_network(): Analyze and Visualize Word Correlation Networks
plot_semantic_viz(): Plot Semantic Analysis Visualization
plot_similarity_heatmap(): Plot Document Similarity Heatmap
plot_cross_category_heatmap(): Plot Cross-Category Similarity Comparison
plot_cluster_terms(): Plot Cluster Top Terms

Topic Modeling

STM, embedding-based, and hybrid models

find_optimal_k(): Find Optimal Number of Topics
fit_embedding_model(): Fit Embedding-based Topic Model
fit_hybrid_model(): Fit Hybrid Topic Model
fit_semantic_model(): Fit Semantic Model
fit_temporal_model(): Fit Temporal Topic Model
auto_tune_embedding_topics(): Auto-tune BERTopic Hyperparameters
assess_embedding_stability(): Assess Embedding Topic Model Stability
get_topic_terms(): Select Top Terms for Each Topic
get_topic_prevalence(): Get Topic Prevalence (Gamma) from STM Model
get_topic_texts(): Convert Topic Terms to Text Strings
calculate_topic_probability(): Calculate Topic Probabilities
calculate_topic_stability(): Calculate Topic Stability
identify_topic_trends(): Identify Topic Trends
generate_topic_labels(): Generate Topic Labels Using OpenAI's API
generate_topic_content(): Generate Content from Topic Terms
plot_topic_probability(): Plot Per-Document Per-Topic Probabilities
plot_topic_effects_categorical(): Plot Topic Effects for Categorical Variables
plot_topic_effects_continuous(): Plot Topic Effects for Continuous Variables
plot_word_probability(): Plot Word Probabilities by Topic
plot_model_comparison(): Plot Topic Model Comparison Scatter
plot_quality_metrics(): Plot Topic Model Quality Metrics
plot_term_trends_continuous(): Plot Term Frequency Trends by Continuous Variable

PDF & Multimodal

Text extraction from PDFs with optional vision AI

process_pdf_unified(): Process PDF File (Unified Entry Point)
process_pdf_file(): Process PDF File
process_pdf_file_py(): Process PDF File using Python
extract_text_from_pdf(): Extract Text from PDF
extract_text_from_pdf_py(): Extract Text from PDF using Python
extract_tables_from_pdf_py(): Extract Tables from PDF using Python
extract_pdf_multimodal(): Extract PDF with Multimodal Analysis
extract_pdf_smart(): Smart PDF Extraction with Auto-Detection
detect_pdf_content_type(): Detect PDF Content Type
detect_pdf_content_type_py(): Detect PDF Content Type using Python

AI Integration

Topic-grounded content generation via local and web-based APIs

check_ollama(): Check if Ollama is Available
list_ollama_models(): List Available Ollama Models
call_ollama(): Call Ollama for Text Generation
call_openai_chat(): Call OpenAI Chat Completion API
call_gemini_chat(): Call Gemini Chat API
call_llm_api(): Call LLM API (Unified Wrapper)
check_vision_models(): Check Vision Model Availability
get_recommended_ollama_model(): Get Recommended Ollama Model
get_best_embeddings(): Get Best Available Embeddings
get_api_embeddings(): Get Embeddings from API
get_spacy_embeddings(): Get spaCy Word Embeddings
run_rag_search(): RAG-Enhanced Semantic Search
analyze_sentiment_llm(): LLM-based Sentiment Analysis
get_content_type_prompt(): Get Default System Prompt for Content Type
get_content_type_user_template(): Get Default User Prompt Template for Content Type

Python Environment

Python environment setup

setup_python_env(): Setup Python Environment
check_python_env(): Check Python Environment Status

Validation

Quality metrics and cross-validation

cross_analysis_validation(): Cross Analysis Validation
validate_cross_models(): Cross-Analysis Validation
validate_semantic_coherence(): Validate Semantic Coherence
calculate_clustering_metrics(): Calculate Clustering Quality Metrics
calculate_cross_similarity(): Calculate Cross-Matrix Cosine Similarity
analyze_similarity_gaps(): Analyze Similarity Gaps Between Categories
extract_cross_category_similarities(): Extract Cross-Category Similarities from Full Similarity Matrix

Data

Example datasets

SpecialEduTech: Special education technology bibliographic data
acronym: Acronym List
stm_15: An example structure of a structural topic model
dictionary_list_1: Dictionary List 1
dictionary_list_2: Dictionary List 2
stopwords_list: Stopwords List