The IBM SPSS Modeler Text Analytics 18.1 User's Guide provides information on how to use the software. The software can be used to extract information from text data and categorize it.
This is the User's Guide for IBM SPSS Modeler Text Analytics version 18.1. It explains how the software uses linguistic technologies and Natural Language Processing (NLP) to process unstructured text data, extract and organize key concepts, and group those concepts into categories that can be combined with structured data for modeling in IBM SPSS Modeler.
The guide walks through reading in source text with the File List, Web Feed and Language nodes; using the Text Mining, Text Link Analysis and File Viewer nodes; and working in interactive workbench mode with the concepts, categories, clusters and text link analysis views. Later chapters cover extraction and categorization techniques, category rules, clusters, graphs, templates and resources, libraries and dictionaries, and text link rules, followed by notices, trademarks and an index.
| Product version | 18.1, release 0, modification 0 |
|---|---|
| Core technology | Advanced linguistic technologies and Natural Language Processing (NLP) |
| Included linguistic resources | Dictionaries for terms and synonyms, libraries, and templates |
| Included domain templates | Custom templates, libraries, and dictionaries for domains such as CRM and genomics |
It processes unstructured text data to extract and organize key concepts, and can then group those concepts into categories.
It uses advanced linguistic technologies and Natural Language Processing (NLP) to rapidly process a large variety of unstructured text data.
It is delivered with dictionaries for terms and synonyms, libraries, and templates, which you can develop and refine for your own context.
Technical support is available to maintenance customers through the IBM Corp. web site.