Automated recognition of emotional states of horses from facial expressions

Marcelo Feighelstein; Claire Riccie-Bonot; Hana Hasan; Hallel Weinberg; Tidhar Rettig; Maya Segal; Tomer Distelfeld; Ilan Shimshoni; Daniel S. Mills; Anna Zamansky

doi:10.1371/journal.pone.0302893

Automated recognition of emotional states of horses from facial expressions

Marcelo Feighelstein, Claire Riccie-Bonot, Hana Hasan, Hallel Weinberg, Tidhar Rettig, Maya Segal, Tomer Distelfeld, Ilan Shimshoni, Daniel S. Mills, Anna Zamansky

Department of Information Systems

Research output: Contribution to journal › Article › peer-review

Abstract

Animal affective computing is an emerging new field, which has so far mainly focused on pain, while other emotional states remain uncharted territories, especially in horses. This study is the first to develop AI models to automatically recognize horse emotional states from facial expressions using data collected in a controlled experiment. We explore two types of pipelines: a deep learning one which takes as input video footage, and a machine learning one which takes as input EquiFACS annotations. The former outperforms the latter, with 76% accuracy in separating between four emotional states: baseline, positive anticipation, disappointment and frustration. Anticipation and frustration were difficult to separate, with only 61% accuracy.

Original language	English
Article number	e0302893
Journal	PLoS ONE
Volume	19
Issue number	7
DOIs	https://doi.org/10.1371/journal.pone.0302893
State	Published - Jul 2024

Bibliographical note

Publisher Copyright:
© 2024 Feighelstein et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

ASJC Scopus subject areas

General

Access to Document

10.1371/journal.pone.0302893

Cite this

@article{0927a4bb0aa14bfe8abdfc0b7f209cc7,

title = "Automated recognition of emotional states of horses from facial expressions",

abstract = "Animal affective computing is an emerging new field, which has so far mainly focused on pain, while other emotional states remain uncharted territories, especially in horses. This study is the first to develop AI models to automatically recognize horse emotional states from facial expressions using data collected in a controlled experiment. We explore two types of pipelines: a deep learning one which takes as input video footage, and a machine learning one which takes as input EquiFACS annotations. The former outperforms the latter, with 76% accuracy in separating between four emotional states: baseline, positive anticipation, disappointment and frustration. Anticipation and frustration were difficult to separate, with only 61% accuracy.",

author = "Marcelo Feighelstein and Claire Riccie-Bonot and Hana Hasan and Hallel Weinberg and Tidhar Rettig and Maya Segal and Tomer Distelfeld and Ilan Shimshoni and Mills, {Daniel S.} and Anna Zamansky",

note = "Publisher Copyright: {\textcopyright} 2024 Feighelstein et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.",

year = "2024",

month = jul,

doi = "10.1371/journal.pone.0302893",

language = "English",

volume = "19",

journal = "PLoS ONE",

issn = "1932-6203",

publisher = "Public Library of Science",

number = "7",

}

TY - JOUR

T1 - Automated recognition of emotional states of horses from facial expressions

AU - Feighelstein, Marcelo

AU - Riccie-Bonot, Claire

AU - Hasan, Hana

AU - Weinberg, Hallel

AU - Rettig, Tidhar

AU - Segal, Maya

AU - Distelfeld, Tomer

AU - Shimshoni, Ilan

AU - Mills, Daniel S.

AU - Zamansky, Anna

N1 - Publisher Copyright: © 2024 Feighelstein et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

PY - 2024/7

Y1 - 2024/7

N2 - Animal affective computing is an emerging new field, which has so far mainly focused on pain, while other emotional states remain uncharted territories, especially in horses. This study is the first to develop AI models to automatically recognize horse emotional states from facial expressions using data collected in a controlled experiment. We explore two types of pipelines: a deep learning one which takes as input video footage, and a machine learning one which takes as input EquiFACS annotations. The former outperforms the latter, with 76% accuracy in separating between four emotional states: baseline, positive anticipation, disappointment and frustration. Anticipation and frustration were difficult to separate, with only 61% accuracy.

AB - Animal affective computing is an emerging new field, which has so far mainly focused on pain, while other emotional states remain uncharted territories, especially in horses. This study is the first to develop AI models to automatically recognize horse emotional states from facial expressions using data collected in a controlled experiment. We explore two types of pipelines: a deep learning one which takes as input video footage, and a machine learning one which takes as input EquiFACS annotations. The former outperforms the latter, with 76% accuracy in separating between four emotional states: baseline, positive anticipation, disappointment and frustration. Anticipation and frustration were difficult to separate, with only 61% accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85198721384&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0302893

DO - 10.1371/journal.pone.0302893

M3 - Article

C2 - 39008504

AN - SCOPUS:85198721384

SN - 1932-6203

VL - 19

JO - PLoS ONE

JF - PLoS ONE

IS - 7

M1 - e0302893

ER -

Automated recognition of emotional states of horses from facial expressions

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this