Replaces each topic's label with a name you choose after reading its
representative texts, for example the kind of message a topic holds
("Correction", "Short hint"). The names replace the label column of
every table keyed by topic, so they appear in
summary(), topic_sizes(),
terms(), representatives(),
predict(), topic_hierarchy(), and every
plot. Nothing is refitted.
Arguments
- object
A fitted
topics()model.- labels
Character vector with one distinct, non-empty name per topic, in topic order (topic 1 first).
Value
The model with its labels replaced: an sbert_topic_model whose
$settings$topic_names records the names. reduce_topics() merges
topics, so it drops the names and labels the merged topics afresh.
Errors
Raises a condition of class sbert_bad_topic_names when
labels is not a character vector with one distinct, non-empty,
non-missing name per topic.
Examples
text <- c(
"Cats chase mice", "Dogs chase balls",
"Stocks and bonds trade", "Markets price shares"
)
embeddings <- rbind(c(1, 0), c(0.9, 0.1), c(0, 1), c(0.1, 0.9))
fitted <- topics(text, 2, embeddings = embeddings)
named <- name_topics(fitted, c("Pets", "Finance"))
topic_sizes(named)
#> topic label n_documents proportion
#> 1 1 Pets 2 0.5
#> 2 2 Finance 2 0.5