Facebook posts can help predict the risk of depression: study

"Social media data contain genome-related markers," said one of Johannes Eichstaedt's researchers at the University of Pennsylvania in the United States. (Reuters)

The language used by people in their Facebook posts predicts a future diagnosis of depression as accurately as the tools clinicians use in the medical setting to screen for the disease, suggest new research. "Social media data contain genome-related markers," said one of Johannes Eichstaedt's researchers at the University of Pennsylvania in the United States.

"With methods surprisingly similar to those used in genomics, we can combine social media data to find these markers. Depression seems to be something quite detectable in this way, "said Eichstaedt. For the study, published in the journal Proceedings of the National Academy of Sciences (PNAS), researchers identified data from nearly 1,200 people agreeing to share Facebook statuses and information from electronic medical records. They then analyzed the statutes with the help of machine learning techniques to distinguish people with a diagnosis of formal depression.

By analyzing data from social networks shared by participants in the months leading up to the diagnosis of depression, researchers found that their algorithm could accurately predict future depression. To build the algorithm, researchers looked at 524,292 Facebook updates from the years leading up to diagnosis for each person suffering from depression and during the same period for control. They determined the most frequently used words and phrases, then modeled 200 subjects to understand what they called "language markers associated with depression."

Finally, they compared how and how often the depressed and control participants used such phrasing. The researchers learned that these markers included emotional, cognitive and interpersonal processes such as hostility and loneliness, sadness and rumination, and that they could predict future depression three months before the first documentation of the disease in a medical file.