Researchers have developed an algorithm that “decodes” pigs’ vocalizations.
Pig Grunts, Barks And Squeals Reveal A Range Of Emotions
Having gathered thousands of recordings of pigs in various contexts, researchers have discovered for the first time that porcine grunts reveal real emotions.
With an algorithm they designed, the European researchers decoded more than 7,000 pig vocalizations as negative (scared or frightened) or positive (happy or excited).
“With this study, we demonstrate that animal sounds provide great insight into their emotions,” said researcher Elodie Briefer of the University of Copenhagen. As the lead author of a study that appears in the journal Scientific Reports, she noted that this is “an important step towards improved animal welfare for livestock.”
Briefer and her colleagues recorded the pigs in both commercial and lab circumstances. Working with pigs, researchers created mock scenarios to evoke nuanced emotions in the middle of the spectrum of positive and negative. For example, pigs were put in one area and supplied with food and toys or placed in an area lacking these stimuli. The researchers also put the pigs in an area with new, unfamiliar objects for them to explore.
During the experiments, the team recorded the swine’s behavior, heart rate and calls. By analyzing thousands of recordings of the pigs’ positive and negative reactions, researchers tried to tell which betrayed negative or positive emotions. Confirming earlier research, more high-frequency calls, such as squeals and screams, were recorded in negative situations. On the other hand, low-frequency calls such as barks and grunts were associated with positive emotions.
Related behavior also revealed emotion. Pigs typically stood still, released repeated vocalizations and attempted escape while in negative surroundings such as a slaughterhouse, according to the study. Positive emotions elicited exploration of their surroundings and having their ears in a forward position.
When pigs were experiencing good vibes, such as when piglets suckled sows or reunited with their littermates, their vocalizations were associated with positive emotions. Bad vibes included separation from sows, fighting between piglets, slaughter and castration.
Also, with further analysis, the team saw in great detail a new pattern of what the swine were experiencing.
“There are clear differences in pig calls when we look at positive and negative situations. In the positive situations, the calls are far shorter, with minor fluctuations in amplitude. Grunts, more specifically, begin high and gradually go lower in frequency. By training an algorithm to recognize these sounds, we can classify 92 percent of the calls to the correct emotion,” Briefer said.
Over the last two decades, more information about animal emotions has led to acceptance that livestock’s mental health is important for the animals’ wellbeing and farmers’ bottom lines. Even so, the concept of animal welfare remains focused on animals’ physical wellbeing, which has led to automatic monitoring of animal health.
But the results of the study may lead to monitoring and responding to animal vocalizations that reveal their mental state. The researchers believe that the algorithm they developed may be a first step toward improved quality of life for swine and other livestock.
“We have trained the algorithm to decode pig grunts. Now, we need someone who wants to develop the algorithm into an app that farmers can use to improve the welfare of their animals,” Briefer said.
Edited by Siân Speakman and Kristen Butler