posterior

Generate the posterior likelihood of speaker given their rates and predicted
dfm frequencies.

internal

Estimates the authors or speakers of texts. Methods developed in Huang, Perry, and Spirling (2020) <doi:10.1017/pan.2019.49>. The model is built on a Bayesian framework in which the distinctiveness of each speaker is defined by how different, on average, the speaker's terms are to everyone else in the corpus of texts. An optional cross-validation method is implemented to select the subset of terms that generate the most accurate speaker predictions. Once a set of terms is selected, the model can be estimated. Speaker distinctiveness and term influence can be recovered from parameters in the model using package functions. Once fitted, the model can be used to predict authorship of new texts.

Christian Baehr

stylest2

Estimating Speakers of Texts

Arthur Spirling

Leslie Huang

posterior function

<dl><dt>log_weights</dt>
<dd>The logged author-level term weights from a stylest2 model.</dd>
<dt>pred_docs_dfm</dt>
<dd>A document-feature matrix for the texts to be predicted.</dd>
<dt>speakers</dt>
<dd>The speaker labels for <code>pred_docs_dfm</code> rows.</dd>
<dt>log_prior</dt>
<dd>A vector of log prior probabilities.</dd></dl>

Arguments

Internal stylest2 function to predict posterior likelihoods of authorship. — posterior

<dl>

<dt>log_weights</dt>
<dd>The logged author-level term weights from a stylest2 model.</dd>


<dt>pred_docs_dfm</dt>
<dd>A document-feature matrix for the texts to be predicted.</dd>


<dt>speakers</dt>
<dd>The speaker labels for <code>pred_docs_dfm</code> rows.</dd>


<dt>log_prior</dt>
<dd>A vector of log prior probabilities.</dd>

</dl>

posterior: Internal stylest2 function to predict posterior likelihoods of authorship.

Description

Usage

Value

Arguments