textProjection: Compute Supervised Dimension Projection and related variables...

In text: Analyses of Text using Transformers Models from HuggingFace, Natural Language Processing and Machine Learning

Compute Supervised Dimension Projection and related variables for plotting words.

Description

Compute Supervised Dimension Projection and related variables for plotting words.

Usage

textProjection(
  words,
  word_embeddings,
  word_types_embeddings,
  x,
  y = NULL,
  pca = NULL,
  aggregation = "mean",
  split = "quartile",
  word_weight_power = 1,
  min_freq_words_test = 0,
  mean_centering = FALSE,
  mean_centering2 = FALSE,
  Npermutations = 10000,
  n_per_split = 50000,
  seed = 1003
)

Arguments

words	(character) Word or text variable to be plotted.
word_embeddings	Word embeddings from textEmbed for the words to be plotted (i.e., the aggregated word embeddings for the "words" parameter).
word_types_embeddings	Word embeddings from textEmbed for individual words (i.e., decontextualized embeddings).
x	Numeric variable that the words should be plotted according to on the x-axes.
y	Numeric variable that the words should be plotted according to on the y-axes (default = NULL, i.e., a 1-dimensional plot is created).
pca	Number of PCA dimensions applied to the word embeddings in the beginning of the function (default = NULL). A number below 1 takes out % of variance; An integer specify number of components to extract. (default is NULL as this setting has not yet been evaluated).
aggregation	(character) Method to aggregate the word embeddings (default = "mean"; see also "min", "max", and "[CLS]").
split	(character) Method to split the axes (default = "quartile" involving selecting lower and upper quartile; see also "mean"). However, if the variable is only containing two different values (i.e., being dichotomous) mean split is used.
word_weight_power	Compute the power of the frequency of the words and multiply the word embeddings with this in the computation of aggregated word embeddings for group low (1) and group high (2). This increases the weight of more frequent words.
min_freq_words_test	(numeric) Option to select words that have occurred a specified number of times (default = 0); when creating the Supervised Dimension Projection line (i.e., single words receive Supervised Dimension Projection and p-value).
mean_centering	(boolean) Separately mean centering the Group 1 split aggregation embedding, and the Group 2 split aggregation embedding
mean_centering2	(boolean) Separately mean centering the G1 and G2 split aggregation embeddings
Npermutations	(numeric) Number of permutations in the creation of the null distribution (default = 10000).
n_per_split	(numeric) Setting to split Npermutations to avoid reaching computer memory limits; set it lower than Npermutations <- and the higher it is set the faster the computation completes, but too high may lead to abortion (default = 50000).
seed	(numeric) Set different seed (default = 1003).

Value

A dataframe with variables (e.g., including Supervised Dimension Projection, frequencies, p-values) for the individual words that is used for the plotting in the textProjectionPlot function.

See Also

See textProjectionPlot.

Examples

# Pre-processing data for plotting.
## Not run: 
df_for_plotting <- textProjection(
  words = Language_based_assessment_data_8$harmonywords,
  word_embeddings = word_embeddings_4$texts$harmonywords,
  word_types_embeddings = word_embeddings_4$word_types,
  x = Language_based_assessment_data_8$hilstotal,
  split = "mean",
  Npermutations = 10,
  n_per_split = 1
)
# Run df_for_plotting to examine result.
df_for_plotting

## End(Not run)

text documentation built on Sept. 11, 2024, 7:22 p.m.