document_network: Build a document network

In bibnets: Importing, Constructing, and Exporting Bibliometric Networks

Build a document network

Description

Constructs a network between documents (papers) in the dataset.

Usage

document_network(
  data,
  type = "coupling",
  counting = "full",
  similarity = "none",
  threshold = 0,
  min_occur = 1L,
  top_n = NULL,
  self_loops = FALSE,
  deduplicate = TRUE,
  format = "edgelist",
  references = "references",
  sep = ";",
  strip_quotes = TRUE,
  id = NULL
)

Arguments

data	A data frame with id and a references column (list-column or delimited string).
type	Character. Relationship type: "coupling" Bibliographic coupling: documents linked when they share cited references. "citation" Direct citation: directed edges from citing to cited documents (internal citations only). "co_citation" Co-citation: documents linked when they are cited together by other documents in the dataset. "equivalence" Profile similarity of reference vectors.
counting	Character. Counting method. Default "full". Position-dependent methods are not applicable to document networks.
similarity	Character. Similarity measure. Default "none".
threshold	Numeric. Minimum edge weight. Default 0.
min_occur	Integer. Minimum reference frequency. Default 1.
top_n	Integer or NULL. Return only the top n edges by weight. Default NULL (all edges).
self_loops	Logical. If TRUE, include self-loops (an entity linked to itself). Default FALSE.
deduplicate	Logical. If TRUE (default), each ⁠(paper, entity)⁠ pair is counted at most once — duplicate entries in the source data (e.g., the same author listed twice on a paper) are treated as one occurrence. Set to FALSE to count every raw occurrence.
format	Character. Output format: "edgelist" Default. A bibnets_network data frame with columns from, to, weight, count. "gephi" Gephi-ready data frame: Source, Target, Weight, Count, Type. "igraph" An igraph graph object (requires igraph). "cograph" A cograph_network object (requires cograph). "matrix" A sparse adjacency matrix.
references	Character. Name of the column containing cited references. Default "references".
sep	Character. Separator used to split the entity column when it is a plain character column rather than a list-column, e.g. sep = "," or sep = " and ". Default ";". Ignored for list-columns. sep applies only to the author column; the references column uses references_sep.
strip_quotes	Logical. If TRUE (default), surrounding quote characters are removed from each reference.
id	Optional. Name of the column to use as the work identifier (the matrix-row dimension). If NULL (default), an existing id column is used when present, otherwise row numbers are used.

Value

Depends on format. For type = "citation", edges are directed (from = citing, to = cited) with weight and count both 1.

Examples

data(biblio_data)
document_network(biblio_data, "coupling")
document_network(biblio_data, "coupling", counting = "strength")

bibnets documentation built on June 19, 2026, 1:06 a.m.