calcscore: Calculate Score Words
In bstewart/stm: Estimation of the Structural Topic Model

calcscore

R Documentation

Calculate Score Words

A primarily internal function for calculating words according to the score metric. We expect most users will use labelTopics instead.

calcscore(logbeta)

logbeta

a K by V matrix containing the log probabilities of seeing word v conditional on topic k

Score is a metric which we include because it is used effectively in the lda package by Jonathan Chang. It is calculated as:

\beta_{v, k} (\log \beta_{w,k} - 1 / K \sum_{k'} \log \beta_{v,k'})

Jonathan Chang (2015). lda: Collapsed Gibbs Sampling Methods for Topic Models. R package version 1.4.2. https://CRAN.R-project.org/package=lda