Extract Cross-Category Similarities from Full Similarity Matrix

Given a full similarity matrix and category information, extracts pairwise similarities between a reference category and other categories into a long-format data frame suitable for visualization and analysis.

Usage

extract_cross_category_similarities(
  similarity_matrix,
  docs_data,
  reference_category,
  compare_categories = NULL,
  category_var = "category",
  id_var = "display_name",
  name_var = NULL
)

Arguments

similarity_matrix

A square similarity matrix (n x n).

docs_data

A data frame containing document metadata with at least:

category_var

Column indicating category membership

id_var

Column with unique document identifiers

reference_category

Character string specifying the reference category to compare against.

compare_categories

Character vector of categories to compare with the reference. If NULL, compares with all categories except reference.

category_var

Name of the column containing category information (default: "category").

id_var

Name of the column containing document IDs (default: "display_name").

name_var

Optional name of column with display names (default: NULL, uses id_var).

Value

A data frame with columns:

ref_id

Reference document ID

ref_name

Reference document name (if name_var provided)

other_id

Comparison document ID

other_name

Comparison document name (if name_var provided)

other_category

Category of comparison document

similarity

Cosine similarity value

See also

Other semantic: analyze_document_clustering(), analyze_similarity_gaps(), calculate_clustering_metrics(), calculate_cross_similarity(), calculate_document_similarity(), calculate_similarity_robust(), cluster_embeddings(), cross_analysis_validation(), export_document_clustering(), fit_semantic_model(), generate_cluster_labels(), generate_cluster_labels_auto(), generate_embeddings(), reduce_dimensions(), semantic_document_clustering(), semantic_similarity_analysis(), temporal_semantic_analysis(), validate_cross_models()

Examples

if (FALSE) { # \dontrun{
# After calculating full similarity matrix
similarity_result <- TextAnalysisR::calculate_document_similarity(
  texts = docs$text,
  document_feature_type = "embeddings"
)

cross_sims <- extract_cross_category_similarities(
  similarity_matrix = similarity_result$similarity_matrix,
  docs_data = docs,
  reference_category = "SLD",
  compare_categories = c("Other Disability", "General"),
  category_var = "category",
  id_var = "display_name",
  name_var = "doc_name"
)
} # }