Related Experiment Video
Updated: May 31, 2026
06:37
Artificial Intelligence-Based System for Detecting Attention Levels in Students
Published on: December 15, 2023
Exploring the Relationship Between Emotion and Bodily Activity With Machine Learning
Roydon Goldsack1, W Bastiaan Kleijn1, Hedwig Eisenbarth1
1Victoria University of Wellington, Wellington, New Zealand.
Psychophysiology
|May 29, 2026
Summary
Machine learning models can predict emotional states from bodily activity. Physiological activity and summative self-reports are more predictable than other measures of emotion.
Area of Science:
- Psychology
- Computer Science
- Affective Computing
Background:
- Human emotional states are linked to bodily activity, but the precise mechanisms remain unclear.
- Investigating this relationship requires robust measures of both bodily activity and emotional experience.
- Previous research suggests physiological activity and body movements are key components of emotional states.
Purpose of the Study:
- To develop a conceptual machine learning model for the relationship between bodily activity and subjective emotional experience.
- To investigate the predictive power of various bodily activity measures on self-reported emotional states.
- To understand which types of emotional measures are more accurately predicted by bodily activity.
Main Methods:
- Recorded full-body movements and physiological activity of participants in dyadic interactions.
- Participants reported their emotional states using three different measures.
- Employed machine learning models to predict self-reported emotions from bodily activity data.
- Utilized linear mixed models to analyze prediction accuracy and interactions.
Main Results:
- Machine learning models demonstrated varying success in predicting emotional states from bodily activity.
- Summative self-report ratings of emotion were found to be more predictable than other measures.
- Physiological activity consistently showed higher predictive relevance for emotional states compared to other bodily measures.
- The intensity of certain emotions was more predictable than others within the models.
Conclusions:
- Machine learning models can effectively predict emotional states using bodily activity data, particularly physiological signals.
- Summative emotional self-reports offer a more predictable target for machine learning-based emotion recognition.
- This study highlights the significant role of physiological activity in understanding and predicting human emotional experiences.
Related Concept Videos
01:16Physiological Theories: James-Lange Theory of Emotion
The James-Lange theory of emotion, proposed by William James and Carl Lange in the late 19th century, asserts that emotions are the result of physiological reactions to external stimuli. Contrary to the traditional view, which suggests that emotions directly arise from the perception of stimuli, this theory proposes that emotions occur as a consequence of the body's responses to such stimuli. According to this framework, an emotional experience is a cognitive interpretation of physiological...
01:20Physiology of Emotion
The physiology of emotions is a multifaceted process involving the autonomic nervous system, brain structures, hormones, and neurotransmitters. This intricate interplay dictates how emotions manifest in the body and influence behavior.
Autonomic Nervous System
The autonomic nervous system (ANS) plays a critical role in emotional responses by regulating involuntary physiological functions. It consists of two main components: the sympathetic and parasympathetic systems. The sympathetic system...
Autonomic Nervous System
The autonomic nervous system (ANS) plays a critical role in emotional responses by regulating involuntary physiological functions. It consists of two main components: the sympathetic and parasympathetic systems. The sympathetic system...
01:20Cognitive Theories: Schachter-Singer Theory of Emotion
Stanley Schachter and Jerome Singer proposed the two-factor theory of emotion, which emphasizes the interplay between physiological arousal and cognitive labeling in forming emotional experiences. This theory suggests that emotions are not simply a result of physiological responses but rather a combination of these responses and the individual's cognitive interpretation of them.
Physiological Arousal and Cognitive Labeling
According to this theory, when an individual experiences physiological...
Physiological Arousal and Cognitive Labeling
According to this theory, when an individual experiences physiological...
01:29Introduction to Motivation and Emotion
Motivation is a multifaceted process that drives behavior toward fulfilling various physiological or psychological needs. This process involves initiating, guiding, and maintaining specific actions influenced by internal and external factors. For example, when someone feels hungry while watching television, hunger is a motivator, prompting the individual to get up, walk to the kitchen, and find something to eat. In this instance, hunger initiates and sustains the behavior necessary to meet the...
01:22Physiological Theories: Cannon-Bard Theory of Emotion
The Cannon-Bard theory of emotion, proposed by Walter Cannon and Philip Bard, challenges the notion that emotions are solely the result of physiological responses. Instead, this theory suggests that emotional experiences and physiological arousal occur simultaneously but operate through independent mechanisms. This dual response is initiated by the brain, specifically by the thalamus, which plays a critical role in processing sensory information.
Upon perceiving a stimulus, such as a dangerous...
Upon perceiving a stimulus, such as a dangerous...
01:20Labeling Emotion
Emotional labeling is a cognitive process that involves identifying and naming one's emotions, such as anger, fear, happiness, or sadness. It allows individuals to recognize and express their internal emotional states, a critical aspect of emotional regulation and communication. Labeling emotions requires more than mere recognition; it also involves drawing upon memory and contextual cues to understand the current situation and apply a corresponding emotional label. For instance, feeling...