Network motifs for translator stylometry identification

Heba El-Fiqi, Eleni Petraki, Hussein A. Abbass

Research output: Contribution to journalArticle

2 Downloads (Pure)

Abstract

Despite the extensive literature investigating stylometry analysis in authorship attribution research, translator stylometry is an understudied research area. The identification of translator stylometry contributes to many fields including education, intellectual property rights and forensic linguistics. In a two stage process, this paper first evaluates the use of existing lexical measures for the translator stylometry problem. Similar to previous research we found that using vocabulary richness in its traditional form as it has been used in the literature could not identify translator stylometry. This encouraged us to design an approach with the aim of identifying the distinctive patterns of a translator by employing network-motifs. Networks motifs are small sub-graphs which aim at capturing the local structure of a complex network. The proposed approach achieved an average accuracy of 83% in three-way classification. These results demonstrate that classic tools based on lexical features can be used for identifying translator stylometry if they get augmented with appropriate non-parametric scaling. Moreover, the use of complex network analysis and network motifs mining provided made it possible to design features that can solve translator stylometry analysis problems.

Original languageEnglish
Pages (from-to)1-33
Number of pages33
JournalPLoS One
Volume14
Issue number2
DOIs
Publication statusPublished - 2019

Fingerprint

Complex networks
Research
Intellectual Property
Authorship
intellectual property rights
Vocabulary
Ownership
Intellectual property
Linguistics
Electric network analysis
education
Education
forensic sciences

Cite this

El-Fiqi, Heba ; Petraki, Eleni ; Abbass, Hussein A. / Network motifs for translator stylometry identification. In: PLoS One. 2019 ; Vol. 14, No. 2. pp. 1-33.
@article{be0d031aacce43aba03ccd8269190989,
title = "Network motifs for translator stylometry identification",
abstract = "Despite the extensive literature investigating stylometry analysis in authorship attribution research, translator stylometry is an understudied research area. The identification of translator stylometry contributes to many fields including education, intellectual property rights and forensic linguistics. In a two stage process, this paper first evaluates the use of existing lexical measures for the translator stylometry problem. Similar to previous research we found that using vocabulary richness in its traditional form as it has been used in the literature could not identify translator stylometry. This encouraged us to design an approach with the aim of identifying the distinctive patterns of a translator by employing network-motifs. Networks motifs are small sub-graphs which aim at capturing the local structure of a complex network. The proposed approach achieved an average accuracy of 83{\%} in three-way classification. These results demonstrate that classic tools based on lexical features can be used for identifying translator stylometry if they get augmented with appropriate non-parametric scaling. Moreover, the use of complex network analysis and network motifs mining provided made it possible to design features that can solve translator stylometry analysis problems.",
author = "Heba El-Fiqi and Eleni Petraki and Abbass, {Hussein A.}",
year = "2019",
doi = "10.1371/journal.pone.0211809",
language = "English",
volume = "14",
pages = "1--33",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

Network motifs for translator stylometry identification. / El-Fiqi, Heba; Petraki, Eleni; Abbass, Hussein A.

In: PLoS One, Vol. 14, No. 2, 2019, p. 1-33.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Network motifs for translator stylometry identification

AU - El-Fiqi, Heba

AU - Petraki, Eleni

AU - Abbass, Hussein A.

PY - 2019

Y1 - 2019

N2 - Despite the extensive literature investigating stylometry analysis in authorship attribution research, translator stylometry is an understudied research area. The identification of translator stylometry contributes to many fields including education, intellectual property rights and forensic linguistics. In a two stage process, this paper first evaluates the use of existing lexical measures for the translator stylometry problem. Similar to previous research we found that using vocabulary richness in its traditional form as it has been used in the literature could not identify translator stylometry. This encouraged us to design an approach with the aim of identifying the distinctive patterns of a translator by employing network-motifs. Networks motifs are small sub-graphs which aim at capturing the local structure of a complex network. The proposed approach achieved an average accuracy of 83% in three-way classification. These results demonstrate that classic tools based on lexical features can be used for identifying translator stylometry if they get augmented with appropriate non-parametric scaling. Moreover, the use of complex network analysis and network motifs mining provided made it possible to design features that can solve translator stylometry analysis problems.

AB - Despite the extensive literature investigating stylometry analysis in authorship attribution research, translator stylometry is an understudied research area. The identification of translator stylometry contributes to many fields including education, intellectual property rights and forensic linguistics. In a two stage process, this paper first evaluates the use of existing lexical measures for the translator stylometry problem. Similar to previous research we found that using vocabulary richness in its traditional form as it has been used in the literature could not identify translator stylometry. This encouraged us to design an approach with the aim of identifying the distinctive patterns of a translator by employing network-motifs. Networks motifs are small sub-graphs which aim at capturing the local structure of a complex network. The proposed approach achieved an average accuracy of 83% in three-way classification. These results demonstrate that classic tools based on lexical features can be used for identifying translator stylometry if they get augmented with appropriate non-parametric scaling. Moreover, the use of complex network analysis and network motifs mining provided made it possible to design features that can solve translator stylometry analysis problems.

UR - http://www.scopus.com/inward/record.url?scp=85061232088&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/network-motifs-translator-stylometry-identification

U2 - 10.1371/journal.pone.0211809

DO - 10.1371/journal.pone.0211809

M3 - Article

VL - 14

SP - 1

EP - 33

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 2

ER -