Show simple item record

dc.contributor.authorMalmasi, Shervin
dc.contributor.authorZampieri, Marcos
dc.date.accessioned2018-03-14T12:28:06Z
dc.date.available2018-03-14T12:28:06Z
dc.date.issued2017-12-13
dc.identifier.citationMalmasi, S., Zampieri, M. (2017) 'Challenges in discriminating profanity from hate speech'. Journal of Experimental & Theoretical Artificial Intelligence, 30 (2), pp. 187-202.
dc.identifier.issn0952-813X
dc.identifier.doi10.1080/0952813X.2017.1409284
dc.identifier.urihttp://hdl.handle.net/2436/621180
dc.description.abstractIn this study, we approach the problem of distinguishing general profanity from hate speech in social media, something which has not been widely considered. Using a new dataset annotated specifically for this task, we employ supervised classification along with a set of features that includes -grams, skip-grams and clustering-based word representations. We apply approaches based on single classifiers as well as more advanced ensemble classifiers and stacked generalisation, achieving the best result of accuracy for this 3-class classification task. Analysis of the results reveals that discriminating hate speech and profanity is not a simple task, which may require features that capture a deeper understanding of the text not always possible with surface -grams. The variability of gold labels in the annotated data, due to differences in the subjective adjudications of the annotators, is also an issue. Other directions for future work are discussed.
dc.language.isoen
dc.publisherTaylor & Francis
dc.relation.urlhttps://www.tandfonline.com/doi/full/10.1080/0952813X.2017.1409284
dc.subjecthate speech
dc.subjectsocial media
dc.subjectbullying
dc.subjectTwitter
dc.subjecttext classification
dc.subjectclassifier ensembles
dc.titleChallenges in discriminating profanity from hate speech
dc.typeJournal article
dc.identifier.journalJournal of Experimental & Theoretical Artificial Intelligence
dc.contributor.institutionHarvard Medical School, Boston, MA, USA.
dc.contributor.institutionResearch Group in Computational Linguistics, University of Wolverhampton, UK.
dc.date.accepted2017-09-19
rioxxterms.funderInternal
rioxxterms.identifier.projectUoW140318MZ
rioxxterms.versionAM
rioxxterms.licenseref.urihttps://creativecommons.org/CC BY-NC-ND 4.0
rioxxterms.licenseref.startdate2018-12-12
dc.source.volume30
dc.source.issue2
dc.source.beginpage187
dc.source.endpage202
refterms.dateFCD2018-10-18T15:47:00Z
refterms.versionFCDAM
html.description.abstractIn this study, we approach the problem of distinguishing general profanity from hate speech in social media, something which has not been widely considered. Using a new dataset annotated specifically for this task, we employ supervised classification along with a set of features that includes -grams, skip-grams and clustering-based word representations. We apply approaches based on single classifiers as well as more advanced ensemble classifiers and stacked generalisation, achieving the best result of accuracy for this 3-class classification task. Analysis of the results reveals that discriminating hate speech and profanity is not a simple task, which may require features that capture a deeper understanding of the text not always possible with surface -grams. The variability of gold labels in the annotated data, due to differences in the subjective adjudications of the annotators, is also an issue. Other directions for future work are discussed.


Files in this item

Thumbnail
Name:
profanity.pdf
Size:
505.6Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record