A SAS text analyst needs to score new documents into an existing latent semantic space created by PROC TEXTMINE's SVD. Which SAS procedure is used for this scoring step?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — PROC TMSCORE is the procedure you use to score new documents into an existing text-mining space. It applies the original vocabulary, IDF weights, and SVD components through the TERMS= option to project the new documents into the same latent dimensions.
Full Explanation
PROC TMSCORE with the TERMS= option pointing to the vocabulary and weights from the original PROC TEXTMINE run is correct because PROC TMSCORE scores new documents into an existing text mining space. It applies the existing vocabulary, IDF weights, and SVD components from the original PROC TEXTMINE run, specified via TERMS=, to parse and project new documents into the same latent dimensions. PROC SCORE with the SVD eigenvectors as the SCORE= matrix is wrong; PROC SCORE handles linear scoring matrices for regression-type models, not text mining SVD. Running PROC TEXTMINE again on the new documents using the MODEL= option to apply the existing vocabulary is wrong; PROC TEXTMINE does not have a MODEL= scoring option. PROC ASTORE with the text model saved as an ASTORE item is wrong; PROC TEXTMINE does not produce ASTORE items.