After I trained my SLDA model with labels, I called SLDA_model.get_regression_coef(). The results contains a L x K matrix, where L is the number of unique labels in my dataset, and K is the number of topics. However, it seems that every row of the matrix is the same. That means every label is equally likely to be associated with each topic. That does not make a lot of sense to me.
I summed the coefficients for every row and they are exactly the same
After I trained my SLDA model with labels, I called SLDA_model.get_regression_coef(). The results contains a L x K matrix, where L is the number of unique labels in my dataset, and K is the number of topics. However, it seems that every row of the matrix is the same. That means every label is equally likely to be associated with each topic. That does not make a lot of sense to me.
I summed the coefficients for every row and they are exactly the same