Improved cyberbullying detection using gender information

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1957 Downloads (Pure)

Abstract

As a result of the invention of social networks, friendships, relationships and social communication are all undergoing changes and new definitions seem to be applicable. One may have hundreds of ‘friends’ without even seeing their faces. Meanwhile, alongside this transition there is increasing evidence that online social applications are used by children and adolescents for bullying. State-of-the-art studies in cyberbullying detection have mainly focused on the content of the conversations while largely ignoring the characteristics of the actors involved in cyberbullying. Social studies on cyberbullying reveal that the written language used by a harasser varies with the author’s features including gender. In this study we used a support vector machine model to train a gender-specific text classifier. We demonstrated that taking gender-specific language features into account improves the discrimination capacity of a classifier to detect cyberbullying.
Original languageUndefined
Title of host publicationProceedings of the Twelfth Dutch-Belgian Information Retrieval Workshop (DIR 2012)
Place of PublicationGhent
PublisherGhent University
Pages23-25
Number of pages4
ISBN (Print)not assigned
Publication statusPublished - 23 Feb 2012
Event12th Dutch-Belgian Information Retrieval Workshop, DIR 2012 - Ghent, Belgium
Duration: 24 Feb 201224 Feb 2012
Conference number: 12

Publication series

Name
PublisherUniversity of Ghent

Workshop

Workshop12th Dutch-Belgian Information Retrieval Workshop, DIR 2012
Abbreviated titleDIR
CountryBelgium
CityGhent
Period24/02/1224/02/12

Keywords

  • Gender distinction
  • Cyberharassment
  • IR-79872
  • METIS-285161
  • Support vector machine
  • EC Grant Agreement nr.: FP7/231507
  • Social Networks
  • Text Mining
  • EWI-21608

Cite this

Dadvar, M., de Jong, F. M. G., Ordelman, R. J. F., & Trieschnigg, R. B. (2012). Improved cyberbullying detection using gender information. In Proceedings of the Twelfth Dutch-Belgian Information Retrieval Workshop (DIR 2012) (pp. 23-25). Ghent: Ghent University.
Dadvar, M. ; de Jong, Franciska M.G. ; Ordelman, Roeland J.F. ; Trieschnigg, Rudolf Berend. / Improved cyberbullying detection using gender information. Proceedings of the Twelfth Dutch-Belgian Information Retrieval Workshop (DIR 2012). Ghent : Ghent University, 2012. pp. 23-25
@inproceedings{af923d24e041439aab3a7fd01c3a7d55,
title = "Improved cyberbullying detection using gender information",
abstract = "As a result of the invention of social networks, friendships, relationships and social communication are all undergoing changes and new definitions seem to be applicable. One may have hundreds of ‘friends’ without even seeing their faces. Meanwhile, alongside this transition there is increasing evidence that online social applications are used by children and adolescents for bullying. State-of-the-art studies in cyberbullying detection have mainly focused on the content of the conversations while largely ignoring the characteristics of the actors involved in cyberbullying. Social studies on cyberbullying reveal that the written language used by a harasser varies with the author’s features including gender. In this study we used a support vector machine model to train a gender-specific text classifier. We demonstrated that taking gender-specific language features into account improves the discrimination capacity of a classifier to detect cyberbullying.",
keywords = "Gender distinction, Cyberharassment, IR-79872, METIS-285161, Support vector machine, EC Grant Agreement nr.: FP7/231507, Social Networks, Text Mining, EWI-21608",
author = "M. Dadvar and {de Jong}, {Franciska M.G.} and Ordelman, {Roeland J.F.} and Trieschnigg, {Rudolf Berend}",
year = "2012",
month = "2",
day = "23",
language = "Undefined",
isbn = "not assigned",
publisher = "Ghent University",
pages = "23--25",
booktitle = "Proceedings of the Twelfth Dutch-Belgian Information Retrieval Workshop (DIR 2012)",

}

Dadvar, M, de Jong, FMG, Ordelman, RJF & Trieschnigg, RB 2012, Improved cyberbullying detection using gender information. in Proceedings of the Twelfth Dutch-Belgian Information Retrieval Workshop (DIR 2012). Ghent University, Ghent, pp. 23-25, 12th Dutch-Belgian Information Retrieval Workshop, DIR 2012, Ghent, Belgium, 24/02/12.

Improved cyberbullying detection using gender information. / Dadvar, M.; de Jong, Franciska M.G.; Ordelman, Roeland J.F.; Trieschnigg, Rudolf Berend.

Proceedings of the Twelfth Dutch-Belgian Information Retrieval Workshop (DIR 2012). Ghent : Ghent University, 2012. p. 23-25.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Improved cyberbullying detection using gender information

AU - Dadvar, M.

AU - de Jong, Franciska M.G.

AU - Ordelman, Roeland J.F.

AU - Trieschnigg, Rudolf Berend

PY - 2012/2/23

Y1 - 2012/2/23

N2 - As a result of the invention of social networks, friendships, relationships and social communication are all undergoing changes and new definitions seem to be applicable. One may have hundreds of ‘friends’ without even seeing their faces. Meanwhile, alongside this transition there is increasing evidence that online social applications are used by children and adolescents for bullying. State-of-the-art studies in cyberbullying detection have mainly focused on the content of the conversations while largely ignoring the characteristics of the actors involved in cyberbullying. Social studies on cyberbullying reveal that the written language used by a harasser varies with the author’s features including gender. In this study we used a support vector machine model to train a gender-specific text classifier. We demonstrated that taking gender-specific language features into account improves the discrimination capacity of a classifier to detect cyberbullying.

AB - As a result of the invention of social networks, friendships, relationships and social communication are all undergoing changes and new definitions seem to be applicable. One may have hundreds of ‘friends’ without even seeing their faces. Meanwhile, alongside this transition there is increasing evidence that online social applications are used by children and adolescents for bullying. State-of-the-art studies in cyberbullying detection have mainly focused on the content of the conversations while largely ignoring the characteristics of the actors involved in cyberbullying. Social studies on cyberbullying reveal that the written language used by a harasser varies with the author’s features including gender. In this study we used a support vector machine model to train a gender-specific text classifier. We demonstrated that taking gender-specific language features into account improves the discrimination capacity of a classifier to detect cyberbullying.

KW - Gender distinction

KW - Cyberharassment

KW - IR-79872

KW - METIS-285161

KW - Support vector machine

KW - EC Grant Agreement nr.: FP7/231507

KW - Social Networks

KW - Text Mining

KW - EWI-21608

M3 - Conference contribution

SN - not assigned

SP - 23

EP - 25

BT - Proceedings of the Twelfth Dutch-Belgian Information Retrieval Workshop (DIR 2012)

PB - Ghent University

CY - Ghent

ER -

Dadvar M, de Jong FMG, Ordelman RJF, Trieschnigg RB. Improved cyberbullying detection using gender information. In Proceedings of the Twelfth Dutch-Belgian Information Retrieval Workshop (DIR 2012). Ghent: Ghent University. 2012. p. 23-25