Social Media Posts Can Predict Depression Diagnoses, A New Analysis Says
Scroll through your Facebook feed, and you’re likely to encounter a barrage of minutes-long recipe videos, memes, and the occasional status update from your grandma. But what if there was a way to reach out to Facebook’s 2.2 billion active monthly users for good, beyond sharing funny cat videos? A new study found that content shared by (consenting) Facebook users could help predict future occurrence of depression in their medical records.
Major depression is one of the most common mental illnesses in America — an estimated 16.2 million U.S. adults, or 6.7 percent of the adult population, have experienced at least one major depressive episode, according to the National Institute of Mental Health. Yet roughly 37 percent of adults who have had major depressive episodes do not undergo treatment. This new study is part of a growing body of research looking into novel screening methods for mental illness via social media.
Published in Proceedings of the National Academy of Sciences, the study assessed the language from a sample of 683 consenting patients’ Facebook status histories. Language predictive of depression included references to sadness, loneliness, hostility, and rumination, as well as a preoccupation with the self in statuses. What’s unique about this study is that it is the first to compare the language people use on Facebook to actual clinical diagnoses in the study participants' electronic medical records. In some cases, the researchers were able to predict future depression diagnoses as much as three months before its appearance in individuals' medical records as a diagnosed condition.
The study builds on a developing body of research into the links between social media and early screening of mental illness. A 2017 study developed computational models to help predict depression and PTSD in Twitter users based on their tweets, going as far as to suggest that onset of depression may be detectable from Twitter data “several months” prior to actual diagnosis. Another study, published in May 2018, looked at negative emotions expressed in Facebook and Twitter status updates, suggesting that each social media platform may have different online cultures that manifest different insights into mental health.
Countless articles have lamented on how the rise of social media has impacted people’s mental health.
"It would be irresponsible to take this tool and use it to say: You’re depressed, you're not depressed," Johannes Eichstaedt, a psychologist at the University of Pennsylvania and co-author of the study, told Wired. He emphasized that the research could eventually become useful for identifying individuals who should follow up with more formal screening processes, like a visit to a clinician.
Even though more research is needed in the field before a mechanism to suggest follow-up screenings could be implemented, social media as a mental health screening tool seems like a promising avenue worth exploring. Countless articles have lamented on how the rise of social media has impacted people’s mental health. But the reality is that, despite these studies, social media use is still ubiquitous. Assuming the technology is only applied to consenting users, if social media itself could become a tool to help screen for mental illness, it could one day help mitigate a problem it may itself contribute to.