Multiple Correspondence Analysis, newspaper discourse and subregister

Abstract This article introduces a new method for grouping keywords and examines the extent to which it also allows analysts explore interaction of discourse subregister. It uses multivariate statistical technique, Multiple Correspondence Analysis, reveal dimensions co-occur across texts corpus. These are then interpreted in terms discourses they contribute within data, thus forming basis corpus-assisted analysis. The approach is demonstrated through analysis that used represent Muslims Islam corpus UK national newspaper articles published on these topics spanning 2010–2019. reveals an between subregister, hence this argues need (corpus-assisted) account subregister as level meaningful variation when analysing press discourse.