Abstract:

The linguistic analysis of text for forensic purposes has been developing rapidly over the past decade. However, the discipline has done so in spite of a lack of established tools, methods or theories. Writers in the field have been contributing to a suite of techniques and methods of analysis and this paper offers some further tools for the statistical analysis of text. A case of alleged plagiarism is investigated through the use of two computer programs: Vocalyse and File Comparison. The discussion demonstrates how a quantitative statistical investigation of hapaxes, unique and common lexical and closed class vocabulary can support a qualitative textual analysis, in order to establish whether a case of plagiarism has occurred. The statistical tools and methods explained are offered as examples for use and development by readers.

Author: Alison Johnson