A Survey on Authorship Analysis Tasks and Techniques

Abstract

Authorship Analysis (AA) is a natural language processing field that examines the previous works of writers to identify the author of a text based on its features. Studies in authorship analysis include authorship identification, authorship profiling, and authorship verification. Due to its relevance, to many applications in this field attention has been paid. It is widely used in the attribution of historical literature. Other applications include legal linguistics, criminal law, forensic investigations, and computer forensics. This paper aims to provide an overview of the work done and the techniques applied in the authorship analysis domain. The examination of recent developments in this field is the principal focus. Many different criteria can be used to define a writer’s style. This paper investigates stylometric features in different author-related tasks, including lexical, syntactic, semantic, structural, and content-specific ones. A lot of classification methods have been applied to authorship analysis tasks. We examine many research studies that use different machine learning and deep learning techniques. As a means of pointing the direction for future studies, we present the most relevant methods recently proposed. The reviewed studies include documents of different types and different languages. In summary, due to the fact that each natural language has its own set of features, there is no standard technique generically applicable for solving the AA problem.

Significance of Single-Interval Discrete Attributes: Case Study on Two-Level Discretisation

“…Attributing authorship is considered the most important stylometric task [28]. It involves two other problems: finding authorial invariants-such sets of features that characterise studied authors; and comparing the writing styles of authors-finding similarities and differentiating the features between them.…”

“…This model is then compared with its equivalent calculated for other texts to verify how close or distant they are. On the other hand, an artificial neural network can be trained based on textual data, or decision rules could be inferred [28]. This last form of representation for discovered knowledge has the huge advantage of being easily accessible, transparent, and having intuitive interpretation.…”

Authorship classification techniques: Bridging textual domains and languages

“…This exploration aims to provide a comprehensive understanding of the methods that have shaped the AA landscape. Misini et al's research [18] offers an extensive exploration of the techniques applied in tasks related to authorship. Dataset repositories.…”

Authorship Attribution in Less-Resourced Languages: A Hybrid Transformer Approach for Romanian

“…Within the domain of authorship attribution, Misini et al [8] identify three distinct tasks, namely, (1) authorship identification [9,10], which aims to identify the author of a given work; (2) authorship profiling or characterization [11][12][13], which explores the demographic traits such as age, gender, or educational level associated with the author; and (3) authorship verification or similarity detection [14], which seeks to establish whether the presumed author aligns with the actual writer of a given document. All these tasks can be formulated as detection problems, where the goal is to determine the degree of similarity between texts by comparing their writing styles.…”