Researchers in Japan have announced that they have developed an AI system that can understand the emotional state of chickens. The study, led by University of Tokyo professor Adrian David Cheok, has not yet been peer-reviewed.
The AI is based on a technique, which can adapt to changing vocal patterns
The study found that the AI system can translate a variety of emotional states in chickens, including hunger, fear, anger, satisfaction, excitement and distress.
The study explains in its paper: “Our methodology uses a cutting-edge AI technique we call Deep Emotional Analysis Learning (DEAL), a highly mathematical and innovative approach that allows for a nuanced understanding of emotional states through auditory data.”
“If we know how animals feel, we can design a much better world for them,” Cheok told the New York Post, which is how the research began. For the study, the researchers tested the system on 80 chickens and collaborated with a team of animal psychologists and veterinarians.
According to the study, the system achieved surprisingly high accuracy in detecting the emotional states of the chickens. The high average detection probabilities for each emotion suggest that the model has learned to capture meaningful patterns and features from the chicken sounds.
The researchers conducted the study taking into account potential limitations, such as racial differences and the complexity of some communications, such as body language.
You can read the full research paper by Adrian Cheok, Jun Cai and Ying Yan here. What do you think? Please don’t forget to share your thoughts with us in the comments.