N-gram analysis in the engineering domain

Abstract

New technologies have enabled the digitization and linguistic analysis of a vast number of books published throughout history. This technology has enabled a step-change in the opportunities to understand the interests of the authors and by doing so provide insight into the aspirations of society throughout published human history. Such analysis provides an unprecedented opportunity, however there are numerous analysis pitfalls due to fundamental technology limitations and misunderstanding of the analysis outcomes. This work defines the technologies which have enabled this opportunity and, in doing so, identifies potential risks of erroneous outcomes. A broad scope analysis of the engineering..