Chapter 8 Corpus analysis and statistics

In this chapter, we will continue using R for the qualitative analyses of textual corpora.

After manipulating the various corpora, we use statistical analyses to provide a statistical account of the corpora. We will use the quanteda package to compute various statistics, including simple frequency analyses, lexical diversity, keyness, collocations, word clouds, network analyses and we will end with Poisson regression that is adapted for count data.