Artificial Neural Network Techniques in Authorship Attribution

Abstract

This paper covers a text classification problem: the identification of the author of a text. It is necessary to find author of a text with given information from a set of candidates whose sample texts were provided. Attempting to solve authorship problems by choosing only features that exist in the anonymous texts did not yield good results. In contrast to other classification tasks, it is not clear which features of a text should be used to classify an author. Also methods that are chosen for classification are important .In this paper, methods for the machine learning of an authorship attribution classifier are investigated using 2 books from each 3 writers as the data set.