An algorithm developed by a research team specializing in K-9 behavior and artificial intelligence (AI) automates evaluating potential working dogs' personalities, according to an article in SciTechDaily.

The researchers hope their discovery will expedite and improve assessing K-9s for long-term success in careers like law enforcement and assisting persons with disabilities, the article noted.

According to the article, scientists, from the University of East London and the University of Pennsylvania, conducted research on behalf of their sponsor Dogvatar, a Miami, Florida-based canine technology startup. They announced the dog personality testing algorithm results in their paper, “An Artificial Intelligence Approach To Predicting Personality Types In Dogs,” published on January 29, 2024, in Scientific Reports, the article noted.

SciTechDaily reported the AI algorithm trained itself using data from nearly 8,000 responses to the Canine Behavioral Assessment & Research Questionnaire (C-BARQ), a 100-question survey that has been the go-to method for assessing working dogs for over 20 years.

According to the report, the AI algorithm creates a digital personality thumbprint for dogs by categorizing the responses to C-BARQ questions. These personality types are identified and described by analyzing the most influential attributes in five categories:

• Excitable/attached

• Anxious/fearful

• Aloof/predatory

• Reactive/assertive

• Calm/agreeable

The data points that feed into those categories include behavioral attributes such as “excitable when the doorbell rings,” “aggression toward unfamiliar dogs visiting your home,” and “chases or would chase birds given the opportunity,” according to the article.

The AI algorithm assigns a "feature importance" value to each attribute, determining its weight in calculating a dog's personality score, researchers said.