word_cloud_plot {scicomptools}

Text Mine a Given Column and Create a Word Cloud

Description

Mines a user-defined column of text and creates a word cloud from the identified words and bigrams.

Usage

word_cloud_plot(
  data = NULL,
  text_column = NULL,
  word_count = 50,
  known_bigrams = c("working group")
)

Arguments

data

dataframe containing at least one column

text_column

character, name of column in dataframe given to 'data' that contains the text to be mined

word_count

numeric, number of words to be returned (counts from most to least frequent)

known_bigrams

character vector, all bigrams (two-word phrases) to be mined before mining for single words

Value

dataframe of one column (named 'word') that can be used for word cloud creation. One row per bigram supplied in 'known_bigrams' or single word (not including "stop words")

Examples

# Create a dataframe containing some example text
text <- data.frame(article_num = 1:6,
                   article_title = c("Why pigeons are the best birds",
                                     "10 ways to show your pet budgie love",
                                     "Should you feed ducks at the park?",
                                     "Locations and tips for birdwatching",
                                     "How to tell which pet bird is right for you",
                                     "Do birds make good pets?"))
                                     
# Prepare the dataframe for word cloud plotting              
word_cloud_prep(data = text, text_column = "article_title")

# Plot the word cloud
word_cloud_plot(data = text, text_column = "article_title")