[ad_1]
Depressed people can be recognized by their language on the Internet
Depression has long become a common illness. As reported by the German foundation Depressionshilfe, about one in four women and one in eight men suffer from at least one depression during their lifetime. But not all patients receive the help they need to overcome the disease. This is because many people do not recognize their illness and are not actively seeking help. US researchers have now developed an algorithm that badyzes social media inputs to filter people with depression or at increased risk of developing depression.
American researchers at the University of Pennsylvania and Stony Brook University have drawn on recent research to decode a sort of depressive linguistic code. From this language code, the science team has programmed an algorithm that badyzes entries on social networks, such as Facebook, to detect alerts from individual users regarding the presence or early development of the Depression. The results of the study were recently published in the famous journal "Proceedings of the National Academy of Sciences" (PNAS).
Recognize depression before it happens
According to the German foundation Depressionshilfe, about 5.3 million people in Germany are affected by depression. The newly developed algorithm could help accurately predict future depression before a medical diagnosis is established. More people might receive help, which is often necessary to overcome a depressive illness.
The language of depression
Several studies have confirmed that depressives use a striking language. This is characterized by negative adjectives such as lonely, sad or unhappy, as well as words such as tears, pain, feelings, loneliness and hostility. In addition, depressed people more often use the ego pronoun "I" but much less pronouns in the second or third person like you, him, she or she.
How Social Media Can Help Diagnose Depression
"What people write on social media reflects an aspect of life that is difficult to access in medicine and research," said author of the study, H. Andrew Schwartz, in a press release about the results of the study. The research team wants to use this information as a marker of disease to uncover depression, anxiety disorders and post-traumatic stress disorder.
Six years of research
Starting from a six-year linguistic badysis, the researchers developed a program capable of detecting and predicting depression among social media users. "Depression seems to be proven this way because affected people are changing the use of social media in a very specific way," Schwartz said. This would not be the case for a skin disease or diabetes.
Similarly good results as a screening test
The researchers badyzed social media data from 1,200 participants. Of these, 114 people suffered from depression. The algorithm should now independently recognize the depressed person. For this, he has traveled more than 500,000 entries. In fact, the program has been successful in detecting depression with as much reliability as current screening tests.
The language changes in a few months
As a control, the researchers evaluated the inflow of depressed people older than six months. Here, in many cases, the algorithm has not detected any depression, suggesting that the language has actually changed.
A discrete depression test?
Johannes Eichstaedt of the University of Pennsylvania, involved in the study, sees a long-term potential in the algorithm. It could be used as a discrete depression test without the affected people having to answer unpleasant questions. He hopes that this program will one day be integrated into the health system. (Vb)
Source link
