Extrapolating continuous color emotions through deep learning
Quantitative Methods
2022-10-18 v1 Machine Learning
Biological Physics
Abstract
By means of an experimental dataset, we use deep learning to implement an RGB 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 typically associate a given emotion with darker colors while females 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.
Cite
@article{arxiv.2009.04519,
title = {Extrapolating continuous color emotions through deep learning},
author = {Vishaal Ram and Laura P. Schaposnik and Nikos Konstantinou and Eliz Volkan and Marietta Papadatou-Pastou and Banu Manav and Domicele Jonauskaite and Christine Mohr},
journal= {arXiv preprint arXiv:2009.04519},
year = {2022}
}
Comments
To appear in Physical Review R. (8 pages, 13 figures)