Corpus Methods in Linguistics – compilation, annotation and statistical analysis

Participants will learn how to: --formulate advanced search queries in a concordancer (e.g. TextSTAT, AntConc) --compile a text corpus with BootCaT --automatically annotate a text corpus in TreeTagger --manually annotate a text corpus in UAM CorpusTool --measure keyword specificity and collocation strength using AntConc --perform exploratory statistical techniques for complexity reduction, such as multiple correspondence analysis and principal components analysis --perform exploratory statistical techniques for classification, such as hierarchical cluster analysis and k-medoid cluster analysis --perform confirmatory statistical analysis such as binary logistic regression and mixed-effects logistic regression