textplot_keyness {quanteda.textplots}

Plot word keyness

Description

Plot the results of a "keyword" of features comparing their differential associations with a target and a reference group, after calculating keyness using quanteda.textstats::textstat_keyness().

Usage

textplot_keyness(
  x,
  show_reference = TRUE,
  show_legend = TRUE,
  n = 20L,
  min_count = 2L,
  margin = 0.05,
  color = c("darkblue", "gray"),
  labelcolor = "gray30",
  labelsize = 4,
  font = NULL
)

Arguments

x

a return object from quanteda.textstats::textstat_keyness()

show_reference

logical; if TRUE, show key reference features in addition to key target features

show_legend

logical; if TRUE, show legend

n

integer; number of features to plot

min_count

numeric; minimum total count of feature across the target and reference categories, for a feature to be included in the plot

margin

numeric; size of margin where feature labels are shown

color

character or integer; colours of bars for target and reference documents. color must have two elements when show_reference = TRUE. See ggplot2::color.

labelcolor

character; color of feature labels.

labelsize

numeric; size of feature labels and bars. See ggplot2::size.

font

character; font-family of texts. Use default font if NULL.

Value

a ggplot2 object

Author(s)

Haiyan Wang and Kohei Watanabe

See Also

quanteda.textstats::textstat_keyness()

Examples

## Not run: 
library("quanteda")
# compare Trump speeches to other Presidents by chi^2
dfmat1 <- data_corpus_inaugural |>
     corpus_subset(Year > 1980) |>
     tokens(remove_punct = TRUE) |>
     tokens_remove(stopwords("en")) |>
     dfm()
dfmat1 <- dfm_group(dfmat1, groups = dfmat1$President)
tstat1 <- quanteda.textstats::textstat_keyness(dfmat1, target = "Trump")
textplot_keyness(tstat1, margin = 0.2, n = 10)
tstat1 <- quanteda.textstats::textstat_keyness(dfmat1, target = "Trump")
textplot_keyness(tstat1, margin = 0.2, n = 10)

# compare contemporary Democrats v. Republicans
corp <- data_corpus_inaugural |>
    corpus_subset(Year > 1960)
corp$party <- ifelse(docvars(corp, "President") %in% c("Nixon", "Reagan", "Bush", "Trump"),
                     "Republican", "Democrat")
dfmat2 <- corp |>
    tokens(remove_punct = TRUE) |>
    tokens_remove(stopwords("en")) |>
    dfm()
tstat2 <- quanteda.textstats::textstat_keyness(dfm_group(dfmat2, groups = dfmat2$party),
                                               target = "Democrat", measure = "lr")
textplot_keyness(tstat2, color = c("blue", "red"), n = 10)

## End(Not run)