Abstract

In order to authorship attribution techniques, the Federalist Papers have been applied as a testing-ground that twelve of which are claimed by Alexander Hamilton and James Madison. The value of novel stylometric techniques through implementation of them to the Federalist problem is what the paper subjects to. Support vector machines and nearest neighbor techniques alongside Artificial Neural Network techniques are used for classification of selected disputed paper. Encouraging results achieved in the research.

Highlights

  • The science which focuses on inferring characteristics of the author from the characteristics of documents that is written by that author is called as authorship attribution as a problem with its long history including a broad spectrum of application.1.1 Authorship AttributionA text of unknown authorship is appointed to one candidate author in a normal authorship attribution problem that a set of candidate authors for whom text samples of undisputed authorship are available as arranged

  • With the attempts for determination of features in order to quantify writing style, research regarding authorship attribution was controlled until the late 1990s that is known as 'stylometry' as a line of research (Holmes, 1994; Holmes, 1998)

  • With a great number of electronic texts available by Internet media including emails, blogs, online forums, etc., the necessity in order to manage the information effectively have increased which resulted with an important impact in scientific areas including information retrieval, machine learning, and natural language processing (NLP), eventually

Read more

Summary

Authorship Attribution

A text of unknown authorship is appointed to one candidate author in a normal authorship attribution problem that a set of candidate authors for whom text samples of undisputed authorship are available as arranged. It can be seen as a multi-class single-label text categorization task according to a machine learning point-of-view (Sebastiani, 2002). With a great number of electronic texts available by Internet media including emails, blogs, online forums, etc., the necessity in order to manage the information effectively have increased which resulted with an important impact in scientific areas including information retrieval, machine learning, and natural language processing (NLP), eventually. Detection, spam email detection as well as finding the authors of disputed or anonymous documents in forensics against cybercrime as to its traditional application as spreading knowledge with respect to the authorship of disputed texts in the classical literature

The Federalist Papers
SUPPORT VECTOR MACHINES
Success of Support Vector Machines
NEAREST NEIGHBOR TECHNIQUE WITH MAHALANOBIS DISTANCE
Success In Nearest Neighbor Technique with Mahalanobis distance
ARTIFICIAL NEURAL NETWORKS
PCA: Principal Component Analysis
ANN Results
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call