Emognition dataset: emotion recognition with self-reports, facial expressions, and physiology using wearables

The Emognition dataset is dedicated to testing methods for emotion recognition (ER) from physiological responses and facial expressions. We collected data from 43 participants who watched short film clips eliciting nine discrete emotions: amusement, awe, enthusiasm, liking, surprise, anger, disgust,...

Full description

Saved in:
Bibliographic Details
Published in:Scientific data 2022-04, Vol.9 (1), p.158-158, Article 158
Main Authors: Saganowski, Stanisław, Komoszyńska, Joanna, Behnke, Maciej, Perz, Bartosz, Kunc, Dominika, Klich, Bartłomiej, Kaczmarek, Łukasz D., Kazienko, Przemysław
Format: Article
Language:English
Subjects:
639/705/117
706/689/477
Anger
Arousal
Data Descriptor
EEG
Emotional behavior
Emotions
Emotions - physiology
Facial Expression
Galvanic skin response
Humanities and Social Sciences
Humans
Motivation
multidisciplinary
Pattern recognition
Physiology
Sadness - psychology
Science
Science (multidisciplinary)
Self Report
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The Emognition dataset is dedicated to testing methods for emotion recognition (ER) from physiological responses and facial expressions. We collected data from 43 participants who watched short film clips eliciting nine discrete emotions: amusement, awe, enthusiasm, liking, surprise, anger, disgust, fear, and sadness. Three wearables were used to record physiological data: EEG, BVP (2x), HR, EDA, SKT, ACC (3x), and GYRO (2x); in parallel with the upper-body videos. After each film clip, participants completed two types of self-reports: (1) related to nine discrete emotions and (2) three affective dimensions: valence, arousal, and motivation. The obtained data facilitates various ER approaches, e.g., multimodal ER, EEG- vs. cardiovascular-based ER, discrete to dimensional representation transitions. The technical validation indicated that watching film clips elicited the targeted emotions. It also supported signals’ high quality. Measurement(s) cardiac output measurement • Electroencephalography • Galvanic Skin Response • Temperature • acceleration • facial expressions Technology Type(s) photoplethysmogram • electroencephalogram (5 electrodes) • electrodermal activity measurement • Sensor • Accelerometer • Video Recording Sample Characteristic - Organism Homo sapiens Sample Characteristic - Environment laboratory environment
ISSN:2052-4463
2052-4463
DOI:10.1038/s41597-022-01262-0