multiple.netfacs.network: Creates network objects out of the netfacs data

In AlexMielke1988/NetFACS: Network Applications to Facial Communication Data

Description

Takes the results of the nefacs object for combinations of 2 elements and turns them into a network object (igraph or sna/network) that can be used for further plotting and analyses

Usage

multiple.netfacs.network(
  netfacs.list,
  link = "unweighted",
  significance = 0.01,
  min.count = 1,
  min.prob = 0,
  ignore.element = NULL
)

Arguments

netfacs.list	list of multiple objects resulting from netfacs() function or the multiple.netfacs() function
link	determines how nodes/elements are connected. 'unweighted' gives a 1 to significant connections and 0 to all others; 'weighted' gives the difference between observed and expected probability of co-occurrence; 'raw' just uses the observed probability of co-occurrence; 'SRI' uses the simple ratio index/affinity (probability of co-occurrence/ (probablities of each element and the combination))
significance	numeric value, determining the p-value below which combinations are considered to be dissimilar enough from the null distribution
min.count	numeric value, suggesting how many times a combination should at least occur to be displayed
min.prob	numeric value, suggesting the probability at which a combination should at least occur to be displayed
ignore.element	vector of elements that will not be considered for the network, e.g. because they are too common or too rare or their interpretation is not relevant here

Value

Function returns a network object where the nodes are the elements, edges represent their co-occurrence, and the vertex and edge attributes contain all additional information from the netfacs object

Examples

data(emotions_set)
emo.faces <- multiple.netfacs(
  data = emotions_set[[1]],
  condition = emotions_set[[2]]$emotion,
  ran.trials = 10, # only for example
  combination.size = 2
)

emo.nets <- multiple.netfacs.network(emo.faces)

AlexMielke1988/NetFACS documentation built on Oct. 27, 2020, 4:14 p.m.