Classification Analysis Of Authorship Fiction Texts in The Space Of Semantic Fields
This work addresses authorship identification for literary analysis, but it is incremental as it applies existing methods to a new semantic feature space.
The study tackled authorship attribution of English fiction texts by analyzing naive Bayesian and k-nearest neighbors classifiers in a vector space based on semantic field frequencies, achieving highly precise classification results.
The use of naive Bayesian classifier (NB) and the classifier by the k nearest neighbors (kNN) in classification semantic analysis of authors' texts of English fiction has been analysed. The authors' works are considered in the vector space the basis of which is formed by the frequency characteristics of semantic fields of nouns and verbs. Highly precise classification of authors' texts in the vector space of semantic fields indicates about the presence of particular spheres of author's idiolect in this space which characterizes the individual author's style.