Listen to this article
Introduction
Understanding the emotions of animals is a key factor in improving their welfare. Pigs are intelligent and social animals, and their emotions are conveyed through a wide range of vocalizations, including grunts. An international team of European researchers has recently developed an automated system that can interpret the emotions encoded in pig grunts, bringing us closer to a very worthy goal: understanding what pigs are feeling.
Methodology
The researchers collected over 7,000 acoustic recordings of 411 pigs throughout their lives in both negative and positive situations in commercial and private farms. The team took these recordings during a wide range of circumstances, which included both positive and negative situations. Positive situations such as piglets suckling from their mothers or being reunited with their families were recorded, as well as negative situations like fights among piglets, separation, castration, or slaughter.
To better discern the emotional reactions of the pigs, the team also created a series of experimental scenarios using commercial pigs. The researchers placed new and unfamiliar objects in an arena for pigs to interact with, monitored their grunts, behavior, and heart rates, and recorded them as much as possible without altering their behavior. The team used these recordings to learn how to translate them into emotions and define the emotions of pigs based on how they naturally react to various external stimuli, and whether stimuli can improve (positive) or threaten (negative) their lives.
Findings
The researchers found that there are clear differences in pig calls when looking at positive and negative situations. Pigs produce more high-frequency sounds (screams and squeals) when experiencing negative emotions. Low-frequency calls (barks and grunts) occurred in either negative or positive situations. These mixed-emotion states were the most interesting, allowing for a much more nuanced interpretation of pig emotional states.
Based on this data, the researchers developed an algorithm and trained it to estimate whether an individual grunt expresses a positive emotion (‘happy’ or ‘excited’), a negative one (‘scared’ or ‘stressed’), or one that falls somewhere in between. The algorithm was able to classify 92% of the calls to the correct emotion.
Typical signs of negative emotions in pigs are standing still, heavy vocalization, and escape behaviors. Signs of positive emotions include exploration of their surroundings and forward posturing of their ears.
Significance
The study reconfirms previous findings that animal sounds provide great insight into their emotions and proves that an algorithm can be used to decode and understand the emotions of pigs, which is an important step towards improved animal welfare for livestock. Associate Professor Elodie Briefer of the University of Copenhagen’s Department of Biology, who co-led the study, states that “the emotional and mental health of livestock is of concern to us, as it is an important element of their overall well-being. Animal welfare today focuses almost exclusively on the physical health of livestock, raising several ethical concerns.”
The researchers propose the use of automated systems to monitor the mental health of animals, analogous to systems that monitor their physiological health. The algorithm described in this study can serve as a basis for such systems, and the team hopes that someone will develop it into an app that farmers can use to improve the welfare of their animals.
Conclusion
In conclusion, the research conducted by the international team of European researchers demonstrates that animal sounds provide great insight into their emotions. By developing an algorithm that can interpret the emotions conveyed in pig grunts, the team has taken an important step towards improving the animal welfare of livestock. The researchers’ work has the potential to allow farmers to better monitor the emotional and mental health of their animals, in addition to their physical health, and can serve as a basis for automated systems that do so.
