EEMCS

Home > Publications
Home University of Twente
Education
Research
Prospective Students
Jobs
Publications
Intranet (internal)
 
 Nederlands
 Contact
 Search
 Organisation

EEMCS EPrints Service


21608 Improved cyberbullying detection using gender information
Home Policy Brochure Browse Search User Area Contact Help

Dadvar, M. and de Jong, F.M.G. and Ordelman, R.J.F. and Trieschnigg, R.B. (2012) Improved cyberbullying detection using gender information. In: Proceedings of the Twelfth Dutch-Belgian Information Retrieval Workshop (DIR 2012), 23-24 Feb 2012, Ghent, Belgium. pp. 23-25. University of Ghent . ISBN not assigned

Full text available as:

PDF

268 Kb
Open Access



Official URL: http://dir2012.intec.ugent.be/system/files/proceedings/DIR2012_04_Maral_Dadvar.pdf

Exported to Metis

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.

Item Type:Conference or Workshop Paper (Full Paper, Talk)
Research Group:EWI-HMI: Human Media Interaction, EWI-DB: Databases
Research Program:CTIT-NICE: Natural Interaction in Computer-mediated Environments
Research Project:Puppy-IR: An Open Source Environment to construct Information Services for Children, FACT: Folktales As Classifiable Texts
Uncontrolled Keywords:Cyberharassment, Gender distinction, Social networks, Support vector machine, Text mining.
ID Code:21608
Status:Published
Deposited On:05 March 2012
Refereed:Yes
International:No
More Information:statisticsmetis

Export this item as:

To correct this item please ask your editor

Repository Staff Only: edit this item