Quantitative analysis of character networks in Polish 19th- and 20th-century novels

Abstract

This article presents a study on induction and quantitative analysis of character networks inferred from Polish novels. The corpus compiled for this study includes both 19th- and 20th-century literary works in the form of electronic editions of novels and OCR-derived texts obtained from publicly available sources. The natural language processing pipeline developed for the purpose of inducing character networks from novels is described. The structural properties of the inferred character networks are investigated, and significant differences between the properties of networks induced from 19th- to 20th-century novels are demonstrated.