Automatic Categorization What's It All About?

• Published in: The Serials librarian Vol. 51; no. 2; pp. 91 - 101
• Main Author: Farmer, Linda
• Format: Journal Article Conference Proceeding
• Language: English
• Published: New York, NY Taylor & Francis Group 08.11.2006; Haworth Press; Taylor & Francis LLC
• Subjects: Automatic categorization; Automatic classification; Category management; Content analysis; digital content; Exact sciences and technology; Human-computer interaction; Indexing. Classification. Abstracting. Syntheses; Information and communication sciences; Information and document structure and analysis; Information management; Information processing and retrieval; Information science. Documentation; Information technology; Metadata; Sciences and techniques of general use; Software utilities; Taxonomies; Text categorization; Vocabularies & taxonomies; Automatic classification; Text analysis; Automatic categorization; human/ computer interaction; digital content; taxonomies; Metadata; Man machine dialogue; Information extraction; Electronic information; Categorization
• ISSN: 0361-526X; 1541-1095
• DOI: 10.1300/J123v51n02_07

Automatic categorization is a new technology designed to control the flood of unstructured, non-indexed, and unorganized digital content that threatens to swamp knowledge workers in corporations and government. Auto-categorization software tools provide the means to categorize digital content according to predefined taxonomies, to extract concepts and entities for the development of taxonomies and to tag content with subject-related metadata tags.This paper describes the primary text-processing technologies employed by auto-categorization tools, outlines the features of the tools and discusses the human/machine interaction required to execute an effective categorization process. This paper is based on the contents of a presentation given at the Canadian Metadata Forum, Ottawa, September 26-28, 2005.