Extrapolating continuous color emotions through deep learning

Détails

Ressource 1Télécharger: Ram_etal_2020_Physical_Review.pdf (2184.49 [Ko])
Etat: Public
Version: Final published version
Licence: CC BY-NC-ND 4.0
ID Serval
serval:BIB_4D0E6E50629D
Type
Article: article d'un périodique ou d'un magazine.
Sous-type
Compte-rendu: analyse d'une oeuvre publiée.
Collection
Publications
Institution
Titre
Extrapolating continuous color emotions through deep learning
Périodique
Physical Review Research
Auteur(s)
Ram Vishaal, Schaposnik Laura P., Konstantinou Nikos, Volkan Eliz, Papadatou-Pastou Marietta, Manav Banu, Jonauskaite Domicele, Mohr Christine
ISSN
2643-1564
Statut éditorial
Publié
Date de publication
09/2020
Peer-reviewed
Oui
Volume
2
Numéro
3
Pages
033350
Langue
anglais
Résumé
By means of an experimental dataset, we use deep learning to implement an RGB (red, green, and blue) extrapolation of emotions associated to color, and do a mathematical study of the results obtained through this neural network. In particular, we see that males (type-m individuals) typically associate a given emotion with darker colors, while females (type-f individuals) associate it with brighter colors. A similar trend was observed with older people and associations to lighter colors. Moreover, through our classification matrix, we identify which colors have weak associations to emotions and which colors are typically confused with other colors.
Mots-clé
colour, emotion, machine learning, neural network
Open Access
Oui
Financement(s)
Fonds national suisse / Projets / 100014_182138
Fonds national suisse / Carrières / P0LAP1_175055
Création de la notice
03/09/2020 13:34
Dernière modification de la notice
09/09/2020 7:08
Données d'usage