The TEXTMINE Procedure

The TEXTMINE procedure integrates natural language processing and statistical analysis to analyze large-scale textual data in SAS Viya. PROC TEXTMINE supports a wide range of fundamental text analysis features, which include tokenizing, stemming, part-of-speech tagging, noun group extraction, default or customized stop lists and start lists, entity parsing, multiword tokens, synonym lists, term weighting, term-by-document matrix creation, dimension reduction with singular value decomposition (SVD), and topic discovery. The procedure leverages the tmMine action of the textMining action set to accomplish these tasks, but it does not surface all of the action’s capabilities. Further functionality is available to you if you call this action directly using PROC CASL.