Corpus analysis and results visualisation using self - organizing maps

This paper addresses the related issues of statistical analysis of text corpora and of intuitivelyaccessible representation of the results of such analysis, with reference to the Newcastle-Poitiers Electronic Corpus of Tyneside English (NPECTE) project. It proposes topographic mapping as a tool for analysis and visualization of the NPECTE corpus, and is in three main parts. The first gives a brief account of the NPECTE project, the second explains the nature of topographic mapping and the motivation for its use, and the third gives an example of how topographic mapping can be implemented using the Self-Organizing Map artificial neural network architecture.