First Impressions Accurately Predicted By New Face Algorithm
Measuring facial features could accurately predict first impressions, according to a new study.
Psychologists at the University of York discovered that it is possible to accurately predict first impressions using measurements of physical features in photographs of faces.
Experts explain that we form judgments about a person's character, like if they're friendly, trustworthy or competent, when looking at a picture of their face. While it is unclear how accurate these initial perceptions influence our behavior, researchers said that first impressions are becoming increasingly important as technology evolves and people get to know one another online rather than in the flesh.
Past studies revealed that people quickly form judgments using three different "dimensions": approachability (do they want to help or harm me?), dominance (can they help or harm me?) and youthful-attractiveness (will they be a good romantic partner - or a rival!).
In the latest study, researchers collected 1,000 ordinary photographs from the Internet and analyzed physical features of the faces. The faces were described in terms of 65 different features such as "eye height", "eyebrow width" and so on.
After combining these calculations, researchers were able to create an algorithm that accurately predict first impressions of more than half of the human raters' social judgments.
Researchers also found that reversing the algorithm made new cartoon-like faces that produced predictable first impressions in a new set of human raters.
Researchers said the latest findings provide scientific insight into the processes that underlie these social judgments. It also shows how important faces and specific images of faces are in creating good and bad first impressions.
"Showing that even supposedly arbitrary features in a face can influence people's perceptions suggests that careful choice of a photo could make (or break) others' first impressions of you," Richard Vernon, a PhD student who was part of the research team, said in a news release.
"We make first impressions of others so intuitively that it seems effortless - I think it's fascinating that we can pin this down with scientific models. I'm now looking at how these first impressions might change depending on different cultural or gender groups of perceivers or faces," added co-researcher Clare Sutherland.
"Showing how these first impressions can be captured from very variable images of faces offers insight into how our brains achieve this seemingly remarkable perceptual feat," Professor Andy Young, of the Department of Psychology at York, said in a statement.
"In everyday life I am not conscious of the way faces and pictures of faces are influencing the way I interact with people. Whether in "real life" or online; it feels as if a person's character is something I can just sense. These results show how heavily these impressions are influenced by visual features of the face - it's quite an eye opener!" added lead researcher Dr Tom Hartley.
The findings are published in the journal Proceedings of the National Academy of Sciences (PNAS).