A SAS Visual Text Analytics pipeline uses topic modeling to discover latent themes in customer feedback. Which algorithm is used by SAS Viya's Text Topic action for probabilistic topic discovery?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — SAS Viya's Text Topic action uses Latent Dirichlet Allocation, a probabilistic generative model. You get documents as mixtures of topics and topics as distributions over words, which is exactly what probabilistic topic discovery means.
Full Explanation
The correct choice is Latent Dirichlet Allocation (LDA) — a probabilistic generative model because SAS Viya's Text Topic action implements LDA, representing documents as mixtures of topics and topics as distributions over words. The option describing Latent Semantic Analysis via singular value decomposition is wrong because it uses SVD, which is deterministic, not probabilistic. The option describing Non-negative Matrix Factorization is wrong because it is a matrix factorization approach distinct from LDA. The option describing K-means clustering of TF-IDF document vectors is wrong because it is hard clustering, not a probabilistic topic model.