conText-class

The <code>conText-class</code> is <code>dgCMatrix class</code> matrix corresponding to
the beta coefficients (embeddings) with additional slots:

internal

context

A fast, flexible and transparent framework to estimate context-specific word and short document embeddings using the 'a la carte'
embeddings approach developed by Khodak et al. (2018) <doi:10.48550/arXiv.1805.05388> and evaluate hypotheses about covariate effects on embeddings using
the regression framework developed by Rodriguez et al. (2021)<doi:10.1017/S0003055422001228>. New version of the package applies a new estimator to measure the distance between word embeddings as described in Green et al. (2025) <doi:10.1017/pan.2024.22>.

Sofia Avila

conText

'a la Carte' on Text (ConText) Embedding Regression

Pedro L. Rodriguez

Arthur Spirling

Brandon Stewart

Christopher Barrie

conText-class function

<dl>
<dt><code>normed_coefficients</code></dt>
<dd><code>normed_betas</code> a data.frame containing the following variables:<dl>
<dt><code>Coefficient</code></dt>
<dd>(character) non-intercept coefficient names</dd></dl></dd></dl><dt><code>Normed_Estimate</code></dt>
<dd>(numeric) norm of non-intercept beta coefficients</dd><dt><code>Std.Error</code></dt>
<dd>(numeric) std errors (given boostrap)</dd><dt><code>Empirical_Pvalue</code></dt>
<dd>(numeric) empirical pvalue (given permute)</dd>

<dt><code>features</code></dt>
<dd>features used in computing the document embeddings</dd>

Slots

Virtual class "conText" for a conText regression output — conText-class

<dl>
<dt><code>normed_coefficients</code></dt>
<dd><code>normed_betas</code> a data.frame containing the following variables:<dl>
<dt><code>Coefficient</code></dt>
<dd>(character) non-intercept coefficient names</dd>

<dt><code>Normed_Estimate</code></dt>
<dd>(numeric) norm of non-intercept beta coefficients</dd>

<dt><code>Std.Error</code></dt>
<dd>(numeric) std errors (given boostrap)</dd>

<dt><code>Empirical_Pvalue</code></dt>
<dd>(numeric) empirical pvalue (given permute)</dd>


</dl></dd>


<dt><code>features</code></dt>
<dd>features used in computing the document embeddings</dd>


</dl>

conText-class: Virtual class "conText" for a conText regression output

Description

Arguments

Slots

See Also