tidy_verbatim: Create a tidy data frame with phrases from each column

In chrisumphlett/openEndedAnalyzeR: Tidy analysis of open-ended survey question responses

Description

This function creates a long table with one row per phrase and column. It allows the user to set the n-gram parameter (how many words per phrase) and then utilizes the tidytext library to unnest each verbatim response. Any NA responses are dropped.

Usage

tidy_verbatim(data, id = id, cols = selected_cols, n = 1)

Arguments

data	Data frame with the survey data
id	Unique survey id. By default, can be omitted if column is named 'id'
cols	List of column(s) to be unnested. By default, can be omitted if using vector named 'selected_cols'
n	Length of phrases, in words. By default is 1 (unigrams)

Details

It's recommended that you select your columns into a vector outside of the function call, because you will probably want to re-use that list with other functions in the package.

Value

A data frame with one row per phrase and column, with survey id.

Examples

data(bloom_survey)
selected_cols <- c("q19verb", "q20verb")
surveys <- tidy_verbatim(bloom_survey, n = 3)

chrisumphlett/openEndedAnalyzeR documentation built on Dec. 25, 2019, 4:10 p.m.