The Role of Linguistic Feature Categories in Authorship Verification

Abstract

Authorship verification is a type of authorship analysis that addresses the following problem: given a set of documents known to be written by an author, and a document of doubtful attribution to that author, the task is to decide whether that document is truly written by that author. A combination of a similarity-based method and relevant linguistic features is used to achieve high accuracy authorship verification. The method is an author-profiling approach that dispenses with negative-evidence training data, and a number of lexical, morphological, and syntactic features and feature ensembles are used to determine optimal feature use. The method-feature combination is applied to a test corpus of 31 Classical Arabic books and substantially outperforms best available baselines (with 87.1% accuracy). The varying performance of different features and feature ensembles indicate that Classical Arabic authors are less free to individualize their style lexically or morphologically than when involving syntactic structures.