diviText: visualizing text segmentation for text mining.

Abstract

Quantitative experiments in text mining often require the segmentation of texts into smaller units. Text segmentation is the process of dividing texts into smaller pieces. This can be done by hand in a text editor, but this is time-consuming and error prone especially when working with large corpora. The diviText tool enables scholars to segment texts in an efficient and accurate way. diviText also produces word counts for use in future clustering and classification analyses.