Authorship attribution on Urdu corpus using lexical, syntactic and stylistic features

Author

Sania Yousuf

Degree

Master of Science in Computer Science

Department

Department of Computer Science

Faculty / School

Faculty of Computer Sciences (FCS)

Date of Submission

2019-12-31

Supervisor

Dr. Muhammad Sarim, Visiting Faculty, Department of Computer Science

Document type

MSCS Survey Report

Keywords

Linguistic stylometry, Syntactic features, Deep learning model.

Abstract

Authorship attribution has deep roots in linguistic Stylometry. Stylometry is the linguistic information to label documents whose authors are unknown by using the writing style of the possible suspects. Traditional authorship attribution systems rely on the specific vocabulary and writing style of the author.

In my study, I have performed two experiments and compare both the experiment and discuss the outcomes. Both experiments examine the performance of the model using the combination of lexical, syntactic and stylistic features. In experiment 1, the performance of Naïve Bayes, Support Vector Machine and Random Forest is examined and in experiment 2, the deep learning model is applied and its performance is judge using the traditional approaches in experiment 1.

Recommended Citation

Yousuf, S. (2019). Authorship attribution on Urdu corpus using lexical, syntactic and stylistic features (Unpublished MSCS survey report). Institute of Business Administration, Pakistan. Retrieved from https://ir.iba.edu.pk/survey-reports-mscs/44