Influence of data discretization on efficiency of Bayesian classifier for authorship attribution

Grzegorz Baron

doi:10.1016/j.procs.2014.08.201

Influence of data discretization on efficiency of Bayesian classifier for authorship attribution

Grzegorz Baron

Department of Graphics, Computer Vision and Digital Systems (RAU/RAU6)

Research output: Contribution to journal › Conference article › peer-review

17 Citations (Scopus)

Abstract

Authorship attribution is one of the research areas in data mining domain and various methods can be employed for performing that task. The paper presents results of research on influence of data discretization on efficiency of Naive Bayes classifier. The analysis has been carried on datasets founded on texts of two male and two female authors using the WEKA data mining software framework. The binary classification was performed separately for both datasets for wide range of parameters of discretization process in order to investigate dependency between ways of discretization and quality of classification using Naive Bayes method. The numerical results of tests have been compared and discussed and some observations and conclusions formulated.

Original language	English
Pages (from-to)	1112-1121
Number of pages	10
Journal	Procedia Computer Science
Volume	35
Issue number	C
DOIs	https://doi.org/10.1016/j.procs.2014.08.201
Publication status	Published - 2014
Event	International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2014 - Gdynia, Poland Duration: 15 Sept 2014 → 17 Sept 2014

Keywords

Authorship attribution
Bayesian classifier
Binarization
Classification
Discretization
Naive Bayes
Stylometry
Text analysis

ASJC Scopus subject areas

General Computer Science

Access to Document

10.1016/j.procs.2014.08.201

Cite this

@article{24e8d2ac6c714932aaa588f6dedc9f69,

title = "Influence of data discretization on efficiency of Bayesian classifier for authorship attribution",

abstract = "Authorship attribution is one of the research areas in data mining domain and various methods can be employed for performing that task. The paper presents results of research on influence of data discretization on efficiency of Naive Bayes classifier. The analysis has been carried on datasets founded on texts of two male and two female authors using the WEKA data mining software framework. The binary classification was performed separately for both datasets for wide range of parameters of discretization process in order to investigate dependency between ways of discretization and quality of classification using Naive Bayes method. The numerical results of tests have been compared and discussed and some observations and conclusions formulated.",

keywords = "Authorship attribution, Bayesian classifier, Binarization, Classification, Discretization, Naive Bayes, Stylometry, Text analysis",

author = "Grzegorz Baron",

note = "Publisher Copyright: {\textcopyright} 2014 The Authors. Published by Elsevier B.V.; International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2014 ; Conference date: 15-09-2014 Through 17-09-2014",

year = "2014",

doi = "10.1016/j.procs.2014.08.201",

language = "English",

volume = "35",

pages = "1112--1121",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier B.V.",

number = "C",

}

TY - JOUR

T1 - Influence of data discretization on efficiency of Bayesian classifier for authorship attribution

AU - Baron, Grzegorz

PY - 2014

Y1 - 2014

N2 - Authorship attribution is one of the research areas in data mining domain and various methods can be employed for performing that task. The paper presents results of research on influence of data discretization on efficiency of Naive Bayes classifier. The analysis has been carried on datasets founded on texts of two male and two female authors using the WEKA data mining software framework. The binary classification was performed separately for both datasets for wide range of parameters of discretization process in order to investigate dependency between ways of discretization and quality of classification using Naive Bayes method. The numerical results of tests have been compared and discussed and some observations and conclusions formulated.

AB - Authorship attribution is one of the research areas in data mining domain and various methods can be employed for performing that task. The paper presents results of research on influence of data discretization on efficiency of Naive Bayes classifier. The analysis has been carried on datasets founded on texts of two male and two female authors using the WEKA data mining software framework. The binary classification was performed separately for both datasets for wide range of parameters of discretization process in order to investigate dependency between ways of discretization and quality of classification using Naive Bayes method. The numerical results of tests have been compared and discussed and some observations and conclusions formulated.

KW - Authorship attribution

KW - Bayesian classifier

KW - Binarization

KW - Classification

KW - Discretization

KW - Naive Bayes

KW - Stylometry

KW - Text analysis

UR - https://www.scopus.com/pages/publications/84924135318

U2 - 10.1016/j.procs.2014.08.201

DO - 10.1016/j.procs.2014.08.201

M3 - Conference article

AN - SCOPUS:84924135318

SN - 1877-0509

VL - 35

SP - 1112

EP - 1121

JO - Procedia Computer Science

JF - Procedia Computer Science

IS - C

T2 - International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2014

Y2 - 15 September 2014 through 17 September 2014

ER -

Influence of data discretization on efficiency of Bayesian classifier for authorship attribution

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this