Decoding Pig Emotions with a Machine Learning Algorithm

We can now decode pigs' emotions. Using thousands of acoustic recordings gathered throughout the lives of pigs, from their births to deaths, an international team of researchers is the first in the world to translate pig grunts into actual emotions across an extended number of conditions and life stages. The research is led by the University of Copenhagen, the ETH Zurich and the France's National Research Institute for Agriculture, Food and Environment (INRAE), and can be used to improve animal welfare in the future.

Is a pig grunt worth a thousand words? Perhaps so. In a new study, an international team of researchers from Denmark, Switzerland, France, Germany, Norway and the Czech Republic have translated pig grunts into emotions. The findings have been published today in Scientific Reports.

Using more than 7,000 audio recordings of pigs, the researchers designed an algorithm that can decode whether an individual pig is experiencing a positive emotion ("happy" or "excited"), a negative one ("scared" or "stressed") or somewhere in between. The recordings were collected in a wide range of situations encountered by commercial pigs, both positive and negative, from when they are born until their deaths.

"With this study, we demonstrate that animal sounds provide great insight into their emotions. We also prove 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," says Associate Professor Elodie Briefer of the University of Copenhagen's Department of Biology at the University of Copenhagen, who co-led the study.

Short grunts are 'happy' grunts

The researchers recorded pig sounds in both commercial and experimental scenarios, which based on the behavior of the pigs, are either associated with a positive or negative emotion. Positive situations included, for example, times when piglets suckle from their mothers or when they are united with their family after being separated. The emotionally negative situations included, among others, separation, fights between piglets, castration and slaughter.

In experimental stables, the researchers also created various mock scenarios for the pigs, designed to evoke more nuanced emotions in the middle of the spectrum. These included an arena with toys or food and a corresponding arena without any stimuli. The researchers also placed new and unfamiliar objects in the arena for the pigs to interact with. Along the way, the pigs' calls, behavior and heartrates were monitored and recorded when possible.

The researchers then analyzed the more than 7,000 audio recordings to see if there was a pattern in the sounds as a function of the emotions, and if they could discern the positive situations and emotions from the negative ones. As already revealed in previous research, the researchers collected more high-frequency calls (such as screams and squeals) in negative situations. At the same time, low-frequency calls (such as barks and grunts) occurred both in situations where the pigs experienced positive or negative emotions.