stylo (version 0.7.5)

stylo.network: Bootstrap consensus networks, with D3 visualization

Description

A function to perform Bootstrap Consensus Network analysys (Eder, 2017), supplemented by interactive visualization (this involves javascript D3). This is a variant of the function stylo, except that it produces final networks without any external software (e.g. Gephi). To use this function, one is required to install the package networkD3.

Usage

stylo.network(mfw.min = 100, mfw.max = 1000, ...)

Value

The function returns an object of the class stylo.results: a list of variables, including a table of word frequencies, vector of features used, a distance table and some more stuff. Additionally, depending on which options have been chosen, the function produces a number of files containing results, plots, tables of distances, etc.

Arguments

mfw.min

the minimal MFW value (e.g. 100 most frequent words) to start the bootstrap procedure with.

mfw.max

the maximum MFW value (e.g. 1000 most frequent words), where procedure should stop. It is required that at least three iterations are completed.

...

any variable produced by stylo.default.settings can be set here, in order to overwrite the default values. An example of such a variable is network = TRUE (switched off as default) for producing stylometric bootstrap consensus networks (Eder, forthcoming); the function saves a csv file, containing a list of nodes that can be loaded into, say, Gephi.

Author

Maciej Eder

Details

The Bootstrap Consensus Network method computes nearest neighborship relations between texts, and then tries to represent them in a form of a network (Eder, 2017). Since multidimensional methods are sensitive to input features (e.g. most frequent words), the methdod produces a series of networks for different MFW settings, and then combines them into a consensus network. To do so, it assumes that both the mininum MFW value and the maximum value is provided. If no additional argument is passed, then the function tries to load text files from the default subdirectory corpus. There are a lot of additional options that should be passed to this function; they are all loaded when stylo.default.settings is executed (which is typically called automatically from inside the stylo function).

References

Eder, M. (2017). Visualization in stylometry: cluster analysis using networks. "Digital Scholarship in the Humanities", 32(1): 50-64.

See Also

stylo

Examples

if (FALSE) {
# standard usage (it builds a corpus from a set of text files):
stylo.networks()

# to take advantage of a dataset provided by the library 'stylo',
# in this case, a selection of Amarican literature from the South
data(lee)
help(lee) # to see what this dataset actually contains
# 
stylo.network(frequencies = lee)
}