Text Mining in Business Intelligence

Text Mining in Business Intelligence

Dan Sullivan (The Ballston Group, USA)
DOI: 10.4018/978-1-59140-206-0.ch006
OnDemand PDF Download:
$37.50

Abstract

As the demand for more effective Business Intelligence (BI) techniques increases, BI practitioners find they must expand the scope of their data to include unstructured text. To exploit those information resources, techniques such as text mining are essential. This chapter describes three fundamental techniques for text mining in business intelligence: term extraction, information extraction, and link analysis. Term extraction, the most basic technique, identifies key terms and logical entities, such as the names of organizations, locations, dates, and monetary amounts. Information extraction builds on terms extracted from text to identify basic relationships, such as the roles of different companies in a merger or the promotion of a chemical reaction by an enzyme. Link analysis combines multiple relationships to form multistep models of complex processes such as metabolic pathways. The discussion of each technique includes an outline of the basic steps involved, characteristics of appropriate applications, and an overview of its limitations.

Complete Chapter List

Search this Book:
Reset