formality: Formality Score

Description

Transcript apply formality score by grouping variable(s) and optionally plot the breakdown of the model.

Usage

formality(
  text.var,
  grouping.var = NULL,
  order.by.formality = TRUE,
  digits = 2,
  ...
)

Value

A list containing at the following components:

text: The text variable
POStagged: Raw part of speech for every word of the text variable
POSprop: Part of speech proportion for every word of the text variable
POSfreq: Part of speech count for every word of the text variable
pos.by.freq: The part of speech count for every word of the text variable by grouping variable(s)
pos.by.prop: The part of speech proportion for every word of the text variable by grouping variable(s)
form.freq.by: The nine broad part of speech categories count for every word of the text variable by grouping variable(s)
form.prop.by: The nine broad part of speech categories proportion for every word of the text variable by grouping variable(s)
formality: Formality scores by grouping variable(s)
pos.reshaped: An expanded formality scores output (grouping, word.count, pos & form.class) by word

Arguments

text.var: The text variable (or an object from pos, pos_by or formality. Passing the later three object will greatly reduce run time.
grouping.var: The grouping variables. Default NULL generates one word list for all text. Also takes a single grouping variable or a list of 1 or more grouping variables.
order.by.formality: logical. If TRUE orders the results by formality score.
digits: The number of digits displayed.
...: Other arguments passed to pos_by.

Warning

Heylighen & Dewaele (2002) state, "At present, a sample would probably need to contain a few hundred words for the measure to be minimally reliable. For single sentences, the F-value should only be computed for purposes of illustration" (p. 24).

Details

Heylighen & Dewaele(2002)'s formality score is calculated as: $$F = 50(\frac{n_{f}-n_{c}}{N} + 1)$$

Where: $$f = \left \{noun, \;adjective, \;preposition, \;article\right \}$$ $$c = \left \{pronoun, \;verb, \;adverb, \;interjection\right \}$$ $$N = \sum{(f \;+ \;c \;+ \;conjunctions)}$$

References

Heylighen, F., & Dewaele, J.M. (2002). Variation in the contextuality of language: An empirical measure. Context in Context, Special issue of Foundations of Science, 7 (3), 293-340.

Examples

Run this code

if (FALSE) {
with(DATA, formality(state, person))
(x1 <- with(DATA, formality(state, list(sex, adult))))
plot(x1)
plot(x1, short.names = FALSE)

scores(x1)
counts(x1)
proportions(x1)
preprocessed(x1)

plot(scores(x1))
plot(counts(x1))
plot(proportions(x1), high="darkgreen")
plot(preprocessed(x1))

data(rajPOS) #A data set consisting of a pos list object
x2 <- with(raj, formality(rajPOS, act))
plot(x2)
cumulative(x2)
x3 <- with(raj, formality(rajPOS, person))
plot(x3, bar.colors="Dark2")
plot(x3, bar.colors=c("Dark2", "Set1"))
x4 <- with(raj, formality(rajPOS, list(person, act)))
plot(x4, bar.colors=c("Dark2", "Set1"))

rajDEM <- key_merge(raj, raj.demographics) #merge demographics with transcript.
x5 <- with(rajDEM, formality(rajPOS, sex))
plot(x5, bar.colors="RdBu")
x6 <- with(rajDEM, formality(rajPOS, list(fam.aff, sex)))
plot(x6, bar.colors="RdBu")
x7 <- with(rajDEM, formality(rajPOS, list(died, fam.aff)))
plot(x7, bar.colors="RdBu",  point.cex=2, point.pch = 3)
x8 <- with(rajDEM, formality(rajPOS, list(died, sex)))
plot(x8, bar.colors="RdBu",  point.cex=2, point.pch = "|")

names(x8)
colsplit2df(x8$formality)

#pass an object from pos or pos_by
ltruncdf(with(raj, formality(x8 , list(act, person))), 6, 4)

#=============#
## ANIMATION ##
#=============#
## EXAMPLE 1
form_ani <- formality(DATA.SPLIT$state, DATA.SPLIT$person)
forma <- Animate(form_ani, contextual="white", formal="blue", 
    current.color = "yellow", current.speaker.color="grey70")

bgb <- vertex_apply(forma, label.color="grey80", size=20, color="grey40")
bgb <- edge_apply(bgb, label.color="yellow")

print(bgb, bg="black", net.legend.color ="white", pause=1)

## EXAMPLE 2
form_ani2 <- formality(raj.act.1POS, mraja1spl$person)
forma2 <- Animate(form_ani2, contextual="white", formal="blue",
    current.color = "yellow", current.speaker.color="grey70")

bgb2 <- vertex_apply(forma2, label.color="grey80", size=17, color="grey40")
bgb2 <- edge_apply(bgb2, label.color="yellow")
print(bgb2, bg="black", pause=.75, net.legend.color = "white")

## EXAMPLE 3 (bar plot)
Animate(form_ani2, as.network=FALSE)

#=====================#
## Complex Animation ##
#=====================#
library(animation)
library(grid)
library(gridBase)
library(qdap)
library(igraph)
library(plotrix)

form_ani2 <- formality(raj.act.1POS, mraja1spl$person)

## Set up the network version
form_net <- Animate(form_ani2, contextual="white", formal="blue",
    current.color = "yellow", current.speaker.color="grey70")
bgb <- vertex_apply(form_net, label.color="grey80", size=17, color="grey40")
bgb <- edge_apply(bgb, label.color="yellow")


## Set up the bar version
form_bar <- Animate(form_ani2, as.network=FALSE)

## Generate a folder
loc <- folder(animation_formality)

## Set up the plotting function
oopt <- animation::ani.options(interval = 0.1)


FUN <- function(follow=FALSE, theseq = seq_along(bgb)) {

    Title <- "Animated Formality: Romeo and Juliet Act 1"
    Legend <- c(.2, -1, 1.5, -.95)
    Legend.cex <- 1

    lapply(theseq, function(i) {
        if (follow) {
            png(file=sprintf("%s/images/Rplot%s.png", loc, i),
                width=650, height=725)
        }
        ## Set up the layout
        layout(matrix(c(rep(1, 9), rep(2, 4)), 13, 1, byrow = TRUE))

        ## Plot 1
        par(mar=c(2, 0, 2, 0), bg="black")
        #par(mar=c(2, 0, 2, 0))
        set.seed(22)
        plot.igraph(bgb[[i]], edge.curved=TRUE)
        graphics::mtext(Title, side=3, col="white")
        color.legend(Legend[1], Legend[2], Legend[3], Legend[4],
              c("Contextual", "Formal"), attributes(bgb)[["legend"]],
              cex = Legend.cex, col="white")

        ## Plot2
        plot.new()
        vps <- baseViewports()

        uns <- unit(c(-1.3,.5,-.75,.25), "cm")
        p <- form_bar[[i]] +
            theme(plot.margin = uns,
                text=element_text(color="white"),
                legend.text=element_text(color="white"),
                legend.background = element_rect(fill = "black"),
                plot.background = element_rect(fill = "black",
                    color="black"))
        print(p,vp = vpStack(vps$figure,vps$plot))
        animation::ani.pause()

        if (follow) {
            dev.off()
        }
    })

}

FUN()

## Detect OS
type <- if(.Platform$OS.type == "windows") shell else system

saveHTML(FUN(, 1:20), autoplay = FALSE, loop = TRUE, verbose = FALSE,
    ani.height = 1000, ani.width=650,
    outdir = loc, single.opts =
    "'controls': ['first', 'play', 'loop', 'speed'], 'delayMin': 0")

FUN(TRUE)

#==================#
## Static Network ##
#==================#
(formdat <- with(sentSplit(DATA, 4), formality(state, person)))
m <- Network(formdat)
m
print(m, bg="grey97", vertex.color="grey75")

print(m, title="Formality Discourse Map", title.color="white", bg="black",
    legend.text.color="white", vertex.label.color = "grey70", 
    edge.label.color="yellow")
    
## or use themes:
dev.off()
m + qtheme()
m + theme_nightheat
dev.off()
m + theme_nightheat(title="Formality Discourse Map", 
    vertex.label.color = "grey50")
    
#===============================#
## Formality Over Time Example ##
#===============================#
formpres <- lapply(with( pres_debates2012, split(dialogue, time)), function(x) {
    formality(x)
})
formplots <- lapply(seq_along(formpres), function(i) {
    m <- plot(cumulative(formpres[[i]]))
    if (i != 2) m <- m + ylab("")
    if (i != 3) m <- m + xlab(NULL)
    m + ggtitle(paste("Debate", i))
})

library(grid)
library(gridExtra)
do.call(grid.arrange, formplots)
}

Run the code above in your browser using DataLab