I'm using the seededLDA
package to do an LDA topic model. However, all of the packages and functions I've found to compute perplexity, log likelihood, exclusivity, etc (and other diagnostic tools) don't work on these models (they only work on topicmodels
LDA outputs).
I didn't use topicmodels
because I need to use seed words, and I haven't been able to get the seeding function in topicmodels
to work.
I really like the look of topicdoc
but that only works on topicmodels
. So, does anyone know how to:
- convert the output from
textmodel
intotopicmodels
; OR - do the diagnostics on
textmodel
outputs?
Thanks in advance, Daniel