To Improve Is to Change: Towards Improving Mood Prediction by Learning Changes in Emotion

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

Abstract

Although the terms mood and emotion are closely related and often used interchangeably, they are distinguished based on their duration, intensity and attribution. To date, hardly any computational models have (a) examined mood recognition, and (b) modelled the interplay between mood and emotional state in their analysis. In this paper, as a first step towards mood prediction, we propose a framework that utilises both dominant emotion (or mood) labels, and emotional change labels on the AFEW-VA database. Experiments evaluating unimodal (trained only using mood labels) and multimodal (trained with both mood and emotion change labels) convolutional neural networks confirm that incorporating emotional change information in the network training process can significantly improve the mood prediction performance, thus highlighting the importance of modelling emotion and mood simultaneously for improved performance in affective state recognition.
Original languageEnglish
Title of host publicationICMI 2022 Companion: Companion Publication of the 24th ACM International Conference on Multimodal Interaction (ICMI 2022)
EditorsRaj Tumuluri, Nicu Sebe, Gopal Pingali, Dinesh Babu Jayagopi
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Pages36-41
Number of pages9
ISBN (Print)9781450393898
DOIs
Publication statusPublished - 7 Nov 2022
Event24th ACM International Conference on Multimodal Interaction - Bengaluru, India
Duration: 7 Nov 202211 Nov 2022
https://icmi.acm.org/2022/

Conference

Conference24th ACM International Conference on Multimodal Interaction
Abbreviated titleICMI 2022
Country/TerritoryIndia
CityBengaluru
Period7/11/2211/11/22
Internet address

Fingerprint

Dive into the research topics of 'To Improve Is to Change: Towards Improving Mood Prediction by Learning Changes in Emotion'. Together they form a unique fingerprint.

Cite this