After researchers from Denmark, Switzerland, France, Germany, Norway, and the Czech Republic analysed thousands of acoustic recordings gathered throughout the lives of captive individuals, they managed to translate vocalisations into emotions across an extended number of conditions and life stages.
Using more than 7000 audio recordings of vocalisations, the researchers designed an algorithm that can interpret whether an individual is experiencing a positive emotion (such as being happy or excited), a negative one (being scared or stressed), or somewhere in between. The research included inmates of all ages, including very young. Emotionally positive situations included breastfeeding, running, and reuniting with family after being separated. The negative situations included separation, short social isolation, fights, mutilation and death. The researchers found that screams were often produced in negative situations, while grunts occurred both in situations where individuals experienced positive or negative emotions.
Elodie Briefer, Associate Professor of the University of Copenhagen’s Department of Biology who co-led the study, said “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% of the calls to the correct emotion.”
In experimental settings, the researchers also created various mock scenarios for the inmates, designed to evoke more subtle emotions. These included areas with toys or food, or without anything. The behaviour and vocalisations of the inmates were measured, and heart rates were monitored and recorded when possible.
The research was led by the University of Copenhagen, the ETH Zurich, and France’s National Research Institute for Agriculture, Food and Environment (INRAE), and it was said it can be used to improve the welfare of inmates in the future. It was published in March 2022 in the journal Scientific Reports, under the title “Classification of pig calls produced from birth to slaughter according to their emotional valence and context of a product.”