Topic Model #1149
-
|
Hello, first I want to thank you for your help and attention to software users. I would like to know if I can say that the topic model can be considered LDA or LSA? Last question, how does the topic model subdivide texts for analysis, which recording unit does it use? |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment
-
|
Hello, thank you for trying KH Coder. Yes, it's LDA with Gibbs sampling using R's "topicmodels" package. R command is: topicmodels::LDA(dtm,
k = 12, # number of topics, user input value
method = "Gibbs",
control = list(
seed = 1234567,
burnin = 1000
)
)Text units vary depending on user selection. When using an Excel file as input, the default units are cells (h5). One cell is considered as one document. You can also change it to "sentences" or "paragraphs". KH Coder separates paragraphs at newline characters.
I am sorry that the English manual is kind of outdated. |
Beta Was this translation helpful? Give feedback.
Hello, thank you for trying KH Coder.
Yes, it's LDA with Gibbs sampling using R's "topicmodels" package. R command is:
Text units vary depending on user selection. When using an Excel file as input, the default units are cells (h5). One cell is considered as one document.
You can also change it to "sentences" or "paragraphs". KH Coder separates paragraphs at newline characters.
I am sorry that the English manual is kind of outdated.