outlier.detect: Detect Outliers in Text

In trinker/qdap2: Bridging the gap between qualitative data and quantitative analysis

Description

Locate possible outliers for text variables given numeric word function.

Usage

  outlier.detect(text.var, grouping.var = NULL,
    FUN = word.count, scale.by = "grouping")

Arguments

text.var	The text variable.
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.
FUN	A word function with a numeric vector output (e.g. syllable.sum, character.count or word.count).
scale.by	A character string indicating which dimensions to scale by. One of "all", "grouping", or "both". Default NULL scales by all.

Value

Returns a dataframe with possible outliers.

Examples

with(DATA, outlier.detect(state))
with(DATA, outlier.detect(state, FUN = character.count))
with(DATA, outlier.detect(state, person, FUN = character.count))
with(DATA, outlier.detect(state, list(sex, adult), FUN = character.count))
with(DATA, outlier.detect(state, FUN = syllable.sum))
htruncdf(with(raj, outlier.detect(dialogue, person)), 15, 45)

trinker/qdap2 documentation built on May 31, 2019, 9:47 p.m.