User manual SAS TEXT MINER 4.2 GETTING STARTED

[. . . ] Getting Started with SAS Text Miner 4. 2 ® SAS® Documentation The correct bibliographic citation for this manual is as follows: SAS Institute Inc. Getting Started with SAS® Text Miner 4. 2. Getting Started with SAS ® Text Miner 4. 2 Copyright © 2010, SAS Institute Inc. , Cary, NC, USA ISBN (electronic book) All rights reserved. Produced in the United States of America. [. . . ] Right-click the Text Miner -- Symptom Text node and select Copy from the menu. Right-click an empty space in the diagram workspace and select Paste. It is important to copy the Text Miner -- Symptom Text node instead of creating a new Text Miner node in order to keep the same property settings you previously configured for the Text Miner -- Symptom Text node. Right-click the new Text Miner node, and select Rename. Type Text Miner -- CST, where "CST" stands for "Cleaned Symptom Text", in the Node Name box. Connect the Data Partition node to the Text Miner -- CST node. 9. Set the following properties in the Properties panel for the Text Miner -- CST node: 36 Chapter 5 · Cleaning Up Text · Click the button for the Synonyms property. Select Mylib to display its contents if it is not already selected. Select Mylib. Vaerextsyn_new from the Select a SAS Table window. Set Terms in a Single Document to No. · 10. Right-click the Text Miner -- CST node, and select Run. Click Yes in the Confirmation dialog box. Click OK in the Run Status dialog box when the node has finished running. Click the button for the Interactive property in the Text Miner -- CST node Properties Panel. The Interactive Results window opens. 12. Select the plus sign (+) next to patient in the Terms table. Note that the misspellings patien, patietn, and patie are included as child terms. Create a Stop List A stop list is a simple collection of low-information or extraneous words that you want to remove from the text, which has been saved as a SAS data set. Click the FREQ column heading to sort the Terms table by frequency. Make sure that the Freq label has an arrow that points downward to indicate that the Freq column is sorted in descending order. Drop some terms that have no bearing on what the adverse reaction is. Hold down the CTRL key and click on these terms: patient, have, receive, vaccine, day, develop, and dose. Select Toggle KEEP to uncheck the Keep attribute. [. . . ] You can also use the Parse properties in the Text Miner node to ignore all parts of speech other than nouns, proper nouns, noun groups, and verbs. Structure sentences properly for best results, including correct grammar, punctuation, and capitalization. Entity extraction does not always generate reasonable results. · · · Dealing with Long Documents SAS Text Miner uses the "bag-of-words" approach to represent documents. That means that documents are represented with a vector that contains the frequency with which each term occurs in each document. [. . . ]