History Education Research in Africa: A Systematic Scoping Review (2013–2023)

The Leximancer system is a relatively new method for transforming lexical co-occurrence information from natural language into semantic patterns in a nunsupervised manner. It employs two stages of co-occurrence information extraction-semantic and relational-using a different algorithm for each stage. The algorithms used are statistical, but they employ nonlinear dynamics and machine learning. This article is an attempt to validate the output of Leximancer, using a set of evaluation criteria taken from content analysis that are appropriate for knowledge discovery tasks.

This paper investigates the potential for Leximancer software to actively support the Grounded Theory (GT) analyst in assessing the “completeness” of their study. The case study takes an existing GT study and retrospectively analyzes the data with Leximancer. The Leximancer output showed encouraging similarities to the main themes emerging from the GT analysis; but not sufficiently at the selective coding level to justifiably claim a definitive cross-check for overall theoretical saturation. Whilst Leximancer is not found to be a substitute for the 'hard labor' of GT coding and theory development, it can provide a very useful, efficient and relatively impartial cross-check of completeness/saturation in the open (and possibly axial) coding stage(s) of a GT study. This automated post-analysis check of GT coding is a novel use of a CAQDAS package.