An artificial intelligence tool is able to predict the age and gender of infants based on temperament. A new study in PLOS ONE employed the powers of machine learning to analyse temperament data of 4,438 babies.
In usual circumstances, differentiating between a newborn boy and girl based on temperament is not easy. When babies turn about a year old, that changes. The machine learning algorithm was able to determine the age of 4,438 babies better than it was able to decipher a baby’s gender based solely on temperament data from an infant’s first 48 weeks.
After this 48-week window passed, the algorithm’s gender classification abilities improved considerably, suggesting that gender differences become more pronounced 48 weeks after a baby is born.
What does this mean? Quite simply, researchers are now able to understand when gender comes into play for human babies. “It is at least suggestive of a picture where temperament begins to differentiate by gender in a more powerful way around age one,” Maria Gartstein, lead author of the study from Washington State University was quoted as saying by TechXplore.
Linking temperament to gender in babies
Previous enquiries into babies’ differences in temperaments based on gender have not looked at the two variables collectively. The problem here was lack of data. To overcome this, the researchers gathered infant behaviour questionnaire data from 2006-19. The questionnaire essentially requires parents to record the frequency of 191 different behaviours in their child after they turn 3 months old and up to a year after their birth. 14 different temperatures metrics are then rated, including smiling, activity levels, anger, and fear. The researchers collected data for 2,298 boys and 2,093 girls for the study’s purpose.
Then, the study’s co-author Erich Seamon from University of Idaho used machine learning algorithms to classify infants as either male or female at different periods – 0-24 weeks of age, 24-48 weeks of age, and older than 48 weeks based “ratings for the 14 temperament dimensions.” The artificial intelligence algorithm’s performance improved as the infant’s age went up.
The researchers found that fear was the most important way to differentiate boys and girls. Their study also reinforces the claim that the effects of socialisation may be felt in infants after they turn a year old.
Source: indiatimes.com
