Automatic Identification of Authors’ Stylistics and Gender on the Basis of the Corpus of Russian Fiction Using Extended Set-theoretic Model with Collocation Extraction

Abstract

We present a novel quantitative approach for classification of authors' stylistics and gender differences based on extraction of word collocation. The proposed algorithm attenuates previously described issues of text processing using the vector models. We demonstrate the approach by analyzing a corpus of Russian prose. We discuss different approaches for classification and identification of the author's style implemented by currently-available software solutions and libraries of morphological analysis, methods of parameterization, indexing of texts, artificial intelligence algorithms and knowledge extraction. Our results demonstrate the efficiency and relative advantage of regression decision tree methods in identifying informative frequency indexes in a way that lends itself to their logical interpretation. We develop a toolkit for conducting comparative experiments to assess the effectiveness of classification of natural language text data, using vector, set-theoretic and the author's set-theoretic with collocation extraction models of text representation. Comparing the ability of different methods to identify the style and gender differences of authors of fiction works, we find that the proposed approach incorporating collocation information alleviates some of the previously identified deficiencies and yields overall improvements in the classification accuracy.