Neural network identification of poets using letter sequences

Abstract

Stylish differences among poets are usually sought in sound and semantics. In human analysis, the criteria for recognizing stylistic differences are manifold and intermingled. This study demonstrates that successful identification of poets based on their work is possible using one criterion: letter sequences. Poets show preferences for certain letter combinations, which are unique to their writing style. Using this criterion in machine computation demonstrates that semantics are not needed to identify poets correctly, and that, as a concession to utter parsimony, one minimal criterion of unique letter sequences is enough to fingerprint an author. A small sample of the work of three Dutch poets was used: Bloem (1887-1966), Slauerhoff (1898-1936), and Lucebert (1924-94). This sample formed the training set for the neural network program to analyse the unique letter patterns for each poet. Next, the program was fed a set of new poems, for which the author was to be identified. In choosing between two poets, the program succeeded in identifying the poet correctly for 80-90% of the new poems. When the choice was between three poets, the score was ∼70% correct. Since raw ASCII files are sufficient as input, and human pre-coding is unnecessary, neural network analysis of letter sequences may turn out to be a powerful tool in categorization and identification problems, such as genre, stylistics, and plagiarism.