UK startup Human is making AI more emotional, with the announcement it’s created Emotional Artificial Intelligence (EAI) software that can work out how someone’s feeling by understanding facial indicators.
Similar to Apple’s FaceID, it identifies facial expressions in real time, measuring what tiny changes in the subject’s face mean. It’s particularly useful for industries such as recruitment, where bias can come into play. For example, a recruiter could be watching a potential candidate in a vide interview and unconsciously is either positively or negatively affected by their gender, race or even their looks.
Human’s technology will take the video, analyse the facial expressions, without any context at all and send the data about their emotional state back to the recruiter. This means they can make a fairer decision about whether the candidate has the right sentiment about the company and the role they’re being interviewed for.
“We look into the micro-expressions,” says Human’s CEO and founder Yi Xu told TechWorld. “These are the milliseconds of movement on the face which the naked human eyes often get wrong.”
“We give a company a combination of the emotion characteristics, and then they interpret that into what the profile looks like. There is no right or wrong. It doesn’t mean that not being passionate is better. It could be that for this particular purpose I want to find someone who is a calmer person, for example, or a less active person.”
However, she said the company doesn’t interpret the data for its clients. Human merely analyses the facial expressions ad send this back to the company to make their own assumptions.
Other applications of the technology could be for fraud detection (analysing how nervous someone is, how they react to stress and how honest they are) or to assess suicide risk in mental health patients.
“They know at certain spots, people have a higher likelihood to commit suicide,” says Yi. “It’s never early enough to prevent these. Now, they want to use a machine to send alerts.”