[ad_1]
People can count on social media such as Facebook to present highlights of their lives, such as vacations. But new research suggests that the language used in publications could also help predict depression.
With the aid of sophisticated software, researchers were able to analyze social media publications and detect depression months before it was apparent on clinical screening tests.
"Social media has allowed people to share some of their everyday life with researchers," said study author Andrew Schwartz, an assistant professor of computer science at Stony Brook University in New York.
"Basically, we used the language that people wrote daily and linked it up to find out if they had a diagnosis of depression," he said.
Watching publications on Facebook "was slightly more accurate than standard selection questions for detecting depression," said Schwartz.
So, what types of language could reveal a person with depression?
The use of first-person pronouns is one of the models observed by researchers. This means that people often use the "I" or the "me" in their social media posts.
Schwartz said people diagnosed as depressed often end up talking about their feelings, their physical pains and their isolation.
But he warned against any attempt to diagnose your friends or family based on a few social media posts.
"One job is not enough to see depression, we were looking at six months of post-diagnosis depression, so I would not recommend people trying to judge their friends and family," he said. declared.
Every year, more than 6% of Americans suffer from depression, noted the study's authors. But less than half receive treatment for the disorder. These high rates of under-diagnosis or under-treatment suggest that current methods of identifying depression could be improved.
The research team was led by Johannes Eichstaedt, PhD student at the University of Pennsylvania.
The investigators had access to Facebook publications from nearly 700 people who had gone to the emergency department of a university center, 114 of whom had been diagnosed with depression. All agreed to share their Facebook information and medical records.
Researchers have examined more than half a million publications on Facebook to create the software algorithm for detecting depression. They determined the most frequently used words and phrases to identify language markers associated with depression.
Using these language markers, researchers were able to predict future depression only three months before it was documented in medical records.
"Social media is attracting a lot of negative attention, but there is a setback: it could be a very powerful tool for the overworked mental health industry," Schwartz said.
The researchers believe this could be a screening tool that clinicians could use to possibly detect depression sooner. But Schwartz also said more studies are needed.
Dr. Alan Geller is a psychiatrist at Gracie Square Hospital in New York City and has not participated in the new study. "Depression is a real problem and preventive treatment is better at saving someone."
"The idea of capturing the risk of someone on Facebook is appealing.Any technology in mental health, especially because we do not have tests like labs or the like. imaging and that we have to rely on what people tell us, could help, "he added.
The study was published online on October 15 in the Proceedings of the National Academy of Sciences.
Image credit:
iStock
[ad_2]
Source link
