Learning Stylometric Representations for Authorship Analysis
This work addresses the scenario-dependent feature selection issue in authorship analysis, which is crucial for applications like cybercrime investigation and psycholinguistics, but it is incremental as it builds on existing neural network techniques.
The paper tackled the problem of manual feature engineering in authorship analysis by proposing a neural network approach that incorporates linguistic features into word representations to learn writing styles from unlabeled texts, achieving superior performance over existing methods like bag-of-lexical-n-grams and word2vec in experiments on Twitter, novel, and essay datasets.
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.