divergence

<code>divergence()</code> computes the regularized topic divergence to find the optimal
number of topics for LDA.

Seeded Sequential LDA can classify sentences of texts into pre-define topics with a small number of seed words (Watanabe & Baturo, 2023) <doi:10.1177/08944393231178605>.
Implements Seeded LDA (Lu et al., 2010) <doi:10.1109/ICDMW.2011.125> and Sequential LDA (Du et al., 2012) <doi:10.1007/s10115-011-0425-1> with the distributed LDA algorithm (Newman, et al., 2009) for parallel computing.

Kohei Watanabe

seededlda

Seeded Sequential LDA for Topic Modeling

Phan Xuan-Hieu

divergence function

<dl><dt>x</dt>
<dd>a LDA model fitted by <code>textmodel_seededlda()</code> or <code>textmodel_lda()</code>.</dd>
<dt>min_size</dt>
<dd>the minimum size of topics for regularized topic divergence.
Ignored when <code>regularize = FALSE</code>.</dd>
<dt>select</dt>
<dd>names of topics for which the divergence is computed.</dd>
<dt>regularize</dt>
<dd>if <code>TRUE</code>, returns the regularized divergence.</dd></dl>

Arguments

Optimize the number of topics — divergence

<dl>

<dt>x</dt>
<dd>a LDA model fitted by <code>textmodel_seededlda()</code> or <code>textmodel_lda()</code>.</dd>


<dt>min_size</dt>
<dd>the minimum size of topics for regularized topic divergence.
Ignored when <code>regularize = FALSE</code>.</dd>


<dt>select</dt>
<dd>names of topics for which the divergence is computed.</dd>


<dt>regularize</dt>
<dd>if <code>TRUE</code>, returns the regularized divergence.</dd>

</dl>

divergence: Optimize the number of topics

Description

Usage

Arguments

Details

References

See Also