Threat detection in online discussions

dc.contributor.author	Wester, Aksel Ladegård
dc.contributor.author	Øvrelid, Lilja
dc.contributor.author	Velldal, Erik
dc.contributor.author	Hammer, Hugo Lewi
dc.date.accessioned	2017-01-25T10:37:10Z
dc.date.accessioned	2017-03-16T09:18:49Z
dc.date.available	2017-01-25T10:37:10Z
dc.date.available	2017-03-16T09:18:49Z
dc.date.issued	2016
dc.identifier.citation	Wester WA, Øvrelid L, Velldal E, Hammer HL: Threat detection in online discussions. In: Balahur A, van der Goot E, Vossen P, Montoyo A. Proceedings of the 7th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis WASSA@NAACL-HLT 2016 (WASSA 2016), 2016. Association for Computational Linguistics p. 66-71	language
dc.identifier.uri	https://hdl.handle.net/10642/4287
dc.description.abstract	This paper investigates the effect of various types of linguistic features (lexical, syntactic and semantic) for training classifiers to detect threats of violence in a corpus of YouTube comments. Our results show that combina- tions of lexical features outperform the use of more complex syntactic and semantic features for this task.	language
dc.title	Threat detection in online discussions	language
dc.type	Chapter
dc.type	Peer reviewed	language
dc.type	Chapter
dc.date.updated	2017-01-25T10:37:10Z
dc.description.version	acceptedVersion	language
dc.identifier.cristin	1375546
dc.source.isbn	978-1-941643-82-2

TKD - Institutt for informasjonsteknologi [1001]
TKD - Department of Computer Science