In general, it is difficult to distinguish with the naked eye the sex or gender of a baby, as well as its exact age. Of course, humans have found a temporary solution to this problem; and it is to fill your newborn with all the gender-segregated signals that can exist.
From earrings and huge 'pink' bows for girls; even hats with blue tassels and t-shirts with elements alluding to what we understand as a society by 'masculinity' for boys. However, artificial intelligence does not need any of these elements, and has already managed to identify its sex based only on its temperament.
The study has been created by professionals from Washington State University, in conjunction with the University of Idaho. To guess the baby's age and gender, the computer used data such as the boys' and girls' propensity to smile, show fear or laugh. This, according to the AI behind it, reveals a lot about the developing person. In fact, there is already an intelligence capable of guessing your gender just by looking at your eyes.
A titanic task
Bonnie Kittle
A questionnaire was applied to measure the baby's temperament. Here, parents were asked to record how often their children experienced some of the 191 different behaviors recorded in infants ages 3 to 12 months. All this, moreover, in just one week.
"These behaviors can be categorized into 14 different dimensions of temperament, such as smile, activity level, anger or frustration, and fear. Overall, the sample collected data from 2,298 boys and 2,093 girls."
How does this AI work?
Using this background, the team was able to develop an artificial intelligence with the ability to identify the sex and age of a baby based on the results obtained.
As they comment from the study, artificial intelligence was able to predict age over sex during the first 48 weeks of the baby's life. However, after this time and as the samples increased in age; this propensity increased on the gender side, confirming that its differences are marked as the infant grows.
Maria Gartstein, lead author of the study and professor of psychology at Washington State University
Of course, there are a lot of influences that can affect both the study and its results. However, the demonstration seems to be sufficiently solid, and indicates that the first signs of socialization between children and their environment begin to become more visible from the first year of age; something that previous studies confirmed. This time, however, it has been an artificial intelligence that helped determine it.
"It was a good opportunity to do a kind of demonstration study using these machine learning techniques that require really large data sets, and which are not very common in socio-emotional development research.
It gave us the opportunity for the first time to really consider the extent to which gender differences are informed by childhood age."
