Automatic Extraction of Keywords from Literary Texts

Conducted from a corpus-driven perspective, this exploratory and targeted research is intended to fill in the gap in corpus linguistics studies on keyness in the literary discourse. More specifically, this empirical study presents a methodology of the automatic detection and description of the use and functions of top keywords and lexical bundles in Margaret Atwood’s fiction. The conducted keyness analysis examines both differences and similarities across focus and reference corpora. The comparison of the key lexical items sheds light both on the affinity and variance of the themes, motifs, and attitudes in the analyzed novels.