From fingerprint to writeprint

L. I. Jiexun, Rong Zheng, Hsinchun Chen

Research output: Contribution to journalArticle

106 Citations (Scopus)

Abstract

Writeprint-based identification is getting very popular in crime investigations due to increasing cybercrime incidents, and unavailability of fingerprints in cybercrime. Writeprint is composed of multiple features, such as vocabulary richness, length of sentence, use of function words, layout of paragraphs, and keywords. These writeprint features can represent an author's writing style, which is usually consistent across his or her writings, and become the basis of authorship analysis. A GA-baased feature selection model to identify writeprint features, can generate different combinations of features to achieve the highest fitness value. These selected key feature of writeprint, corresponding to the high accuracy of classification, is able to effectively represent the distinct writing style of author and can assist in identifying the authorship of online messages.

Original languageEnglish (US)
Pages (from-to)76-82
Number of pages7
JournalCommunications of the ACM
Volume49
Issue number4
StatePublished - 2006

Fingerprint

Crime
Fingerprint
Feature extraction
Selection Model
Feature Model
Feature Selection
Fitness
Layout
High Accuracy
Distinct
Style
Gas

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Graphics and Computer-Aided Design
  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Jiexun, L. I., Zheng, R., & Chen, H. (2006). From fingerprint to writeprint. Communications of the ACM, 49(4), 76-82.

From fingerprint to writeprint. / Jiexun, L. I.; Zheng, Rong; Chen, Hsinchun.

In: Communications of the ACM, Vol. 49, No. 4, 2006, p. 76-82.

Research output: Contribution to journalArticle

Jiexun, LI, Zheng, R & Chen, H 2006, 'From fingerprint to writeprint', Communications of the ACM, vol. 49, no. 4, pp. 76-82.
Jiexun, L. I. ; Zheng, Rong ; Chen, Hsinchun. / From fingerprint to writeprint. In: Communications of the ACM. 2006 ; Vol. 49, No. 4. pp. 76-82.
@article{c1ef797c84a14cc7a546cef67652a7aa,
title = "From fingerprint to writeprint",
abstract = "Writeprint-based identification is getting very popular in crime investigations due to increasing cybercrime incidents, and unavailability of fingerprints in cybercrime. Writeprint is composed of multiple features, such as vocabulary richness, length of sentence, use of function words, layout of paragraphs, and keywords. These writeprint features can represent an author's writing style, which is usually consistent across his or her writings, and become the basis of authorship analysis. A GA-baased feature selection model to identify writeprint features, can generate different combinations of features to achieve the highest fitness value. These selected key feature of writeprint, corresponding to the high accuracy of classification, is able to effectively represent the distinct writing style of author and can assist in identifying the authorship of online messages.",
author = "Jiexun, {L. I.} and Rong Zheng and Hsinchun Chen",
year = "2006",
language = "English (US)",
volume = "49",
pages = "76--82",
journal = "Communications of the ACM",
issn = "0001-0782",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

TY - JOUR

T1 - From fingerprint to writeprint

AU - Jiexun, L. I.

AU - Zheng, Rong

AU - Chen, Hsinchun

PY - 2006

Y1 - 2006

N2 - Writeprint-based identification is getting very popular in crime investigations due to increasing cybercrime incidents, and unavailability of fingerprints in cybercrime. Writeprint is composed of multiple features, such as vocabulary richness, length of sentence, use of function words, layout of paragraphs, and keywords. These writeprint features can represent an author's writing style, which is usually consistent across his or her writings, and become the basis of authorship analysis. A GA-baased feature selection model to identify writeprint features, can generate different combinations of features to achieve the highest fitness value. These selected key feature of writeprint, corresponding to the high accuracy of classification, is able to effectively represent the distinct writing style of author and can assist in identifying the authorship of online messages.

AB - Writeprint-based identification is getting very popular in crime investigations due to increasing cybercrime incidents, and unavailability of fingerprints in cybercrime. Writeprint is composed of multiple features, such as vocabulary richness, length of sentence, use of function words, layout of paragraphs, and keywords. These writeprint features can represent an author's writing style, which is usually consistent across his or her writings, and become the basis of authorship analysis. A GA-baased feature selection model to identify writeprint features, can generate different combinations of features to achieve the highest fitness value. These selected key feature of writeprint, corresponding to the high accuracy of classification, is able to effectively represent the distinct writing style of author and can assist in identifying the authorship of online messages.

UR - http://www.scopus.com/inward/record.url?scp=33745213523&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745213523&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:33745213523

VL - 49

SP - 76

EP - 82

JO - Communications of the ACM

JF - Communications of the ACM

SN - 0001-0782

IS - 4

ER -