A US firm is flogging facial-expression software to analyse job candidates' performance in video interviews and make initial selections for companies including Unilever.
The Marmite and Persil maker has previously used facial recognition software to analyse shoppers' reactions to in-store displays of products, and is now turning to algorythms to help in choosing its workforce.
Hirevue software claims to analyse facial expressions and language to select the best candidates.
Job seekers sit in front of a laptop or mobile phone and complete an automated video interview. This is analysed and compared against results from candidates who have already proved to be good at the job, according to The Telegraph.
Hirevue claims to have already carried out 100,000 interviews for companies in the UK. Most of the analysis is based on language – word choice, tone, speed of speech and sentence length are all considered. But the software also looks at facial expressions – smiling, brow raising and eye widening.
Loren Larsen, CTO at Hirevue, said: "There are 350-ish features that we look at in language: do you use passive or active words? Do you talk about 'I' or 'We.' What is the word choice or sentence length? In doctors, you might expect a good one to use more technical language.
"Then we look at the tone of voice. If someone speaks really slowly, you are probably not going to stay on the phone to buy something from them. If someone speaks at 400 words a minute, people are not going to understand them. Empathy is a piece of that."
People are then ranked on a 1-100 score system.
The company claims it provides a less biased system than one based on the vagaries of a human recruiter.
But UK privacy campaigner Big Brother Watch described the idea as "chilling" – warning that unless the original dataset was extremely diverse, it is very likely to be prejudiced in some way against certain types of candidate.
The lobby group added that the inevitable simplifications of the system would make it biased against unconventional candidates whose expressions, or comfort with a video interview, were out of step with the pre-defined "norm". ®