plot_word_topic_series | R Documentation |
Displays the allocation among topics of a given word. This is a useful diagnostic for models of corpora that are spread over time. The Gibbs sampling state must be loaded. Many analogous plots that condition word weights on two or more variables are possible; see the package vignette for a description of how they can be constructed.
plot_word_topic_series(m, word, n = n_topics(m), breaks = "years")
m |
|
word |
a word found in the model vocabulary |
n |
number of topics to include in plot. The cut is made by ranking
topics according to their overall totals of |
breaks |
time periodicity of the series |
A ggplot object.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.