| nas {sweater} | R Documentation |
Calculate Normalized Association Score
Description
This functions quantifies the bias in a set of word embeddings by Caliskan et al (2017). In comparison to WEAT introduced in the same paper, this method is more suitable for continuous ground truth data. See Figure 1 and Figure 2 of the original paper. If possible, please use query() instead.
Usage
nas(w, S_words, A_words, B_words, verbose = FALSE)
Arguments
w |
a numeric matrix of word embeddings, e.g. from |
S_words |
a character vector of the first set of target words. In an example of studying gender stereotype, it can include occupations such as programmer, engineer, scientists... |
A_words |
a character vector of the first set of attribute words. In an example of studying gender stereotype, it can include words such as man, male, he, his. |
B_words |
a character vector of the second set of attribute words. In an example of studying gender stereotype, it can include words such as woman, female, she, her. |
verbose |
logical, whether to display information |
Value
A list with class "nas" containing the following components:
-
$Pa vector of normalized association score for every word in S -
$rawa list of raw results used for calculating normalized association scores -
$S_wordsthe input S_words -
$A_wordsthe input A_words -
$B_wordsthe input B_words
References
Caliskan, A., Bryson, J. J., & Narayanan, A. (2017). Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334), 183-186. doi:10.1126/science.aal4230