| Title: | Interacting with Roberts and Utych's (2019) Gendered Language Dictionary |
| Version: | 1.0.0 |
| Description: | Allows users to generate a gendered language score according to the gendered language dictionary in Roberts and Utych (2019) <doi:10.1177/1065912919874883>. |
| License: | MIT + file LICENSE |
| Encoding: | UTF-8 |
| RoxygenNote: | 7.2.3 |
| Depends: | R (≥ 2.10) |
| LazyData: | true |
| Suggests: | devtools, knitr, rmarkdown, testthat |
| VignetteBuilder: | knitr |
| URL: | https://gencounter.app.damoncroberts.com, https://damoncharlesroberts.github.io/genCountR/ |
| NeedsCompilation: | no |
| Packaged: | 2023-12-05 00:37:50 UTC; dcr |
| Author: | Damon Roberts 
[aut, cre] |
| Maintainer: | Damon Roberts <damon.charles.roberts@gmail.com> |
| Repository: | CRAN |
| Date/Publication: | 2023-12-05 17:50:04 UTC |
genCountR: Interacting with Roberts and Utych's (2019) Gendered Language Dictionary
Description
Allows users to generate a gendered language score according to the gendered language dictionary in Roberts and Utych (2019) doi:10.1177/1065912919874883.
Author(s)
Maintainer: Damon Roberts damon.charles.roberts@gmail.com (ORCID)
See Also
Useful links:
Data from Gendered Language Dictionary Developed by Roberts and Utych (2019)
Description
Each word in the dataset contains a rating by human coders. See details of dataset in the original paper.
Usage
dict
Format
A tibble with 701 rows and 15 columns:
- Word
The word to match
- POS
Part Of Speech
- mean.a
Mean score provided by all participants
- std.dev.a
Standard deviation of score provided by all participants
Source
https://journals.sagepub.com/doi/10.1177/1065912919874883
gen_count
Description
Counts the number of masculine and feminine words in the document
Usage
gen_count(text)
Arguments
text |
(string): A string object. |
Details
Takes the number of words that are loosely categorized as Masculine, Feminine, or Neutral based on Roberts and Utych's (2019) definition. Feminine words had a score below 2.5, Neutral words had a score higher than 2.5 and lower than 5.5, Masculine words had a score higher than 5.5.
Value
data.frame with each word from the dictionary matched with the text and its number of occurances.
Examples
text <- 'This person was a heroine due to their fighting during the war.'
result_df <- genCountR::gen_count(text)
gen_score
Description
Calculates the score of the supplied text string based on the Gendered Language Dictionary created by Roberts and Utych (2019).
Usage
gen_score(text)
Arguments
text |
(string): A string object |
Details
Takes the matched words and their occurrence in the supplied text, finds the score for those matched words in the dictionary, sums those scores up and then divides it by the total number of words in the dictionary.
Value
list object with avg_score of the supplied text string, total_score of supplied text string, and data.frame of matches
Examples
text <- 'Hero. hero Heroine. heroine, Prison. Prisom.'
result <- genCountR::gen_score(text)
result$avg_score
result$total_score
result$df
text_clean
Description
Cleans the supplied text string and converts it into a list of individual words.
Usage
text_clean(text)
Arguments
text |
(string): A string object. |
Details
Takes the string, converts all the characters to lower case, removes punctuation, and splits the string into individual words.
Value
list of each word in all lower case and without punctuation.
word_count
Description
Count number of times a particular word from the dictionary shows up in a document.
Usage
word_count(word_item)
Arguments
word_item |
(vector or array): A vector or array of words from the text wanting to be matched to dictionary. |
Details
Takes the number of words that are loosely categorized as Masculine, Feminine, or Neutral based on Roberts and Utych's (2019) definition. Feminine words had a score below 2.5, Neutral words had a score higher than 2.5 and lower than 5.5, Masculine words had a score higher than 5.5.
Value
data.frame object of with count of masculine, feminine, and masculine words.