Everyone has heard chickens cluck, but are these random utterings, or could artificial intelligence (AI) help us understand why the chicken crossed the road?
It’s not a laughing matter because the field of machine learning could genuinely unlock practical measures in animal communication or at least a more precise understanding of the emotional state of animals, including our favorite egg-layers.
AI Studies into Chicken Communication
An early study into interspecies communication, focusing on the understanding of chicken vocalizations, was held by University of Tokyo professor Adrian David Cheok.
The study’s objective was to understand the various emotional states in a chicken, such as fear, happiness, anger, hunger, distress, and excitement.
Cheok worked with eight veterinary surgeons and animal psychologists, using a sample size of 80 chickens and 200 hours of recordings.
AI was used to label each sound with an emotional state, with the panel also adding input before machine learning could assess a probability distribution over possible emotional states on new recordings.
Professor Cheok said” “We hope to be able to adapt these AI and ML techniques to other animals and lay the groundwork for incredible intelligence in various animal-related industries. If we know what animals feel, we can design a better world for them”.”
You can extrapolate what further research in this field could bring, from communication with pets to livestock monitoring on farms to understanding animals in their natural habitat.
The team behind the study claims the results are 80% accurate, although the research is in the pre-print stage: a first-draft version of a research paper or a manuscript that has not gone through peer review.
The world of artificial intelligence revolves around humans and machines, and it’s nice to see animals being included, particularly if they can break down language barriers and understand what is going on in our avian friend’s minds, let alone the rest of the animal kingdom.
However, the research is at a fledgling state, and there is a long way to go. We naturally invite all research to be done non-invasive and ethically, but we look forward to seeing where this field goes.