A Study on Affect Model Validity: Nominal vs Ordinal Labels

dc.contributor.author	Melhart, David	en
dc.contributor.author	Sfikas, Konstantinos	en
dc.contributor.author	Giannakakis, Giorgos	en
dc.contributor.author	Yannakakis, Georgios N.	en
dc.contributor.author	Liapis, Antonios	en
dc.date.accessioned	2019-02-16T19:10:28Z
dc.date.available	2019-02-16T19:10:28Z
dc.date.issued	2019-02-16
dc.identifier.uri	http://hdl.handle.net/11400/20233
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.title	A Study on Affect Model Validity: Nominal vs Ordinal Labels	en
heal.type	conferenceItem
heal.language	en
heal.access	free
heal.publicationDate	2018
heal.bibliographicCitation	David Melhart, Konstantinos Sfikas, Giorgos Giannakakis, Georgios N. Yannakakis and Antonios Liapis: "A Study on Affect Model Validity: Nominal vs Ordinal Labels" in Proceedings of the IJCAI workshop on AI and Affective Computing, 2018	en
heal.abstract	The question of representing emotion computationally remains largely unanswered: popular approaches require annotators to assign a magnitude (or a class) of some emotional dimension, while an alternative is to focus on the relationship between two or more options.Recent evidence in affective computing suggests that following a methodology of ordinal annotations and processing leads to better reliability and validity of the model. This pa-per compares the generality of classification methods versus preference learning methods in predicting the levels of arousal in two widely used affective datasets. Findings of this initial study further validate the hypothesis that approaching affect labels as ordinal data and building models via preference learning yields models of better validity.	en
heal.sponsor	This publication is part of a project that has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 693150	en
heal.fullTextAvailability	false
heal.conferenceName	2018 IJCAI workshop on AI and Affective Computin	en
heal.conferenceItemType	full paper