Learning Stylometric Representations for Authorship Analysis

TL;DR

This paper introduces a neural network-based method that combines various linguistic features to learn stylometric representations for authorship analysis, outperforming traditional text representation techniques.

Contribution

It proposes a novel approach integrating topical, lexical, syntactical, and character-level features into distributed representations for authorship tasks.

Findings

Outperforms bag-of-lexical-n-grams and other embedding methods

Effective on Twitter, novel, and essay datasets

Improves accuracy in authorship characterization and verification

Abstract

Authorship analysis (AA) is the study of unveiling the hidden properties of authors from a body of exponentially exploding textual data. It extracts an author's identity and sociolinguistic characteristics based on the reflected writing styles in the text. It is an essential process for various areas, such as cybercrime investigation, psycholinguistics, political socialization, etc. However, most of the previous techniques critically depend on the manual feature engineering process. Consequently, the choice of feature set has been shown to be scenario- or dataset-dependent. In this paper, to mimic the human sentence composition process using a neural network approach, we propose to incorporate different categories of linguistic features into distributed representation of words in order to learn simultaneously the writing style representations based on unlabeled texts for authorship analysis. In particular, the proposed models allow topical, lexical, syntactical, and character-level feature vectors of each document to be extracted as stylometrics. We evaluate the performance of our approach on the problems of authorship characterization and authorship verification with the Twitter, novel, and essay datasets. The experiments suggest that our proposed text representation outperforms the bag-of-lexical-n-grams, Latent Dirichlet Allocation, Latent Semantic Analysis, PVDM, PVDBOW, and word2vec representations.