Linguistic red flags from Facebook posts can predict future depression diagnoses

October 15, 2018, University of Pennsylvania
Credit: CC0 Public Domain

In any given year, depression affects more than 6 percent of the adult population in the United States—some 16 million people—but fewer than half receive the treatment they need. What if an algorithm could scan social media and point to linguistic red flags of the disease before a formal medical diagnosis had been made?

New research from the University of Pennsylvania and Stony Brook University published in the Proceedings of the National Academy of Sciences shows this is now more plausible than ever. Analyzing data shared by consenting users across the months leading up to a diagnosis, the researchers found their algorithm could accurately predict future depression. Indicators of the condition included mentions of hostility and loneliness, words like "tears" and "feelings," and use of more first-person pronouns like "I" and "me."

"What people write in social media and online captures an aspect of life that's very hard in medicine and research to access otherwise," says H. Andrew Schwartz, senior paper author and a principal investigator of the World Well-Being Project (WWBP). "It's a dimension that's relatively untapped compared to biophysical markers of disease. Considering conditions such as depression, anxiety, and PTSD, for example, you find more signals in the way people express themselves digitally."

For six years, the WWBP, based in Penn's Positive Psychology Center and Stony Brook's Human Language Analysis Lab, has been studying how the words people use reflect inner feelings and contentedness. In 2014, Johannes Eichstaedt, WWBP founding research scientist, started to wonder whether it was possible for social media to predict outcomes, particularly for depression.

"Social media data contain markers akin to the genome," Eichstaedt explains. "With surprisingly similar methods to those used in genomics, we can comb to find these markers. Depression appears to be something quite detectable in this way; it really changes people's use of social media in a way that something like skin disease or diabetes doesn't."

Eichstaedt and Schwartz teamed with colleagues Robert J. Smith, Raina Merchant, David Asch, and Lyle Ungar from the Penn Medicine Center for Digital Health for this study. Rather than do what previous studies had done—recruit participants who self-reported depression—the researchers identified data from people consenting to share Facebook statuses and electronic medical-record information, and then analyzed the statuses using machine-learning techniques to distinguish those with a formal depression diagnosis.

"This is early work from our Social Mediome Registry from the Penn Medicine Center for Digital Health," Merchant says, "which joins social media with data from health records. For this project, all individuals are consented, no data is collected from their network, the data is anonymized, and the strictest levels of privacy and security are adhered to."

Nearly 1,200 people consented to provide both digital archives. Of these, just 114 people had a diagnosis of depression in their medical records. The researchers then matched every person with a diagnosis of depression with five who did not have such a diagnosis, to act as a control, for a total sample of 683 people (excluding one for insufficient words within status updates). The idea was to create as realistic a scenario as possible to train and test the researchers' algorithm.

"This is a really hard problem," Eichstaedt says. "If 683 people present to the hospital and 15 percent of them are depressed, would our algorithm be able to predict which ones? If the algorithm says no one was depressed, it would be 85 percent accurate."

To build the algorithm, Eichstaedt, Smith, and colleagues looked back at 524,292 Facebook updates from the years leading to diagnosis for each individual with depression and for the same time span for the control. They determined the most frequently used words and phrases and then modeled 200 topics to suss out what they called "depression-associated language markers." Finally, they compared in what manner and how frequently depressed versus control participants used such phrasing.

They learned that these markers comprised emotional, cognitive, and interpersonal processes such as hostility and loneliness, sadness and rumination, and that they could predict future depression as early as three months before first documentation of the illness in a medical record.

"There's a perception that using social media is not good for one's mental health," Schwartz says, "but it may turn out to be an important tool for diagnosing, monitoring, and eventually treating it. Here, we've shown that it can be used with clinical records, a step toward improving mental health with social media."

Eichstaedt sees long-term potential in using these data as a form of unobtrusive screening. "The hope is that one day, these screening systems can be integrated into systems of care," he says. "This tool raises yellow flags; eventually the hope is that you could directly funnel people it identifies into scalable treatment modalities."

Despite some limitations to the study, including its strictly urban sample, and limitations in the field itself—not every depression diagnosis in a medical record meets the gold standard that structured clinical interviews provide, for example—the findings offer a potential new way to uncover and get help for those suffering from depression.

Explore further: AI could be used to predict outcomes for people at risk of psychosis and depression

More information: Johannes C. Eichstaedt el al., "Facebook language predicts depression in medical records," PNAS (2018). www.pnas.org/cgi/doi/10.1073/pnas.1802331115

Related Stories

AI could be used to predict outcomes for people at risk of psychosis and depression

September 26, 2018
Machine learning, also known as artificial intelligence, could be a useful tool for predicting how well people at high risk of psychosis or with recent onset depression will function socially in the future, an international ...

At-risk adolescents are less likely to express depression on social media as they age

May 5, 2018
Findings from a new study reveal at-risk adolescents are less likely to post about depressive symptoms on social media as they age. The research suggests that adolescents with a diagnosis of depression may feel less stigmatized ...

Taking a closer look at online social networking and depression

November 28, 2016
Comparing yourself with others on Facebook is more likely to lead to feelings of depression than making social comparisons offline.

Depression striking more young people than ever

May 11, 2018
(HealthDay)—Americans are fast becoming a very depressed lot.

Social media use found to contribute to good mental health for many

December 9, 2016
According to new research by academics from University of Melbourne and Monash University, using social networking sites such as Facebook, Twitter and Myspace contributes to good mental health for many users.

Study shows social media content may hold keys to important health information

October 13, 2015
Language used in everyday social media posts may have a strong connection to an individual's health, according to new research from the Perelman School of Medicine at the University of Pennsylvania. In the first study of ...

Recommended for you

Neuroimaging study reveals 'hot spot' for cue-reactivity in substance-dependent population

November 20, 2018
When patients with dependence on alcohol, cocaine or nicotine are shown drug cues, or images related to the substance, an area of their brain known as the medial prefrontal cortex (mPFC) shows increased activity, report investigators ...

Being fair: The benefits of early child education

November 20, 2018
Children from low-income families who got intensive education early in life treat others with high levels of fairness in midlife, more than 40 years later, even when being fair comes at a high personal cost, according to ...

Does Netflix's '13 Reasons Why' influence teen suicide? Survey asks at-risk youths

November 20, 2018
A significant proportion of suicidal teens treated in a psychiatric emergency department said that watching the Netflix series "13 Reasons Why" had increased their suicide risk, a University of Michigan study finds.

MDMA makes people cooperative, but not gullible

November 19, 2018
New research from King's College London has found that MDMA, the main ingredient in ecstasy, causes people to cooperate better—but only with trustworthy people. In the first study to look in detail at how MDMA impacts cooperative ...

Exploring the genetic contribution to suicide risk

November 19, 2018
Researchers at University of Utah Health identified four gene changes that occur more frequently in people who died by suicide that may point to increased risk in vulnerable individuals.

Response to daily stressors could affect brain health in older adults

November 19, 2018
Taking typical daily annoyances such as a long wait at the doctor's office or a traffic jam on the freeway in stride may help preserve brain health in older adults, while emotional reactions could contribute to declines in ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.