The content of your Facebook posts could predict whether you will develop schizophrenia or mood disorders, according to a new study.
The findings were based on machine learning algorithms of users’ “linguistic footprint” utilized by Northwell Health’s Feinstein Institutes for Medical Research and computer scientists at IBM.
The study, published in Nature Partner Journals Schizophrenia, found that those with schizophrenia or mood disorders were more likely to use curse words in Facebook instant messages compared to healthy volunteers.
Participants with mood disorders also tapped more words related to blood and pain — and used “negative emotion” language such as the words “sad,” “upset” and “down” more frequently than healthy participants.
Schizophrenia patients used more perception words – like “hear,” “see” and “feel” and emphatic punctuation.
The words used were fed into a analytics program called Linguistic Inquiry Word Count.
The study also noted that participants with the schizophrenic spectrum disorders posted images that were smaller than healthy volunteers, while those with mood disorders posted photos with colors containing more blue and less yellow.
The research is part of an emerging field of psychiatrics that analyzes patients’ communications and behavior on social media, which could lead to earlier and better diagnosis and intervention for psychiatric care.
The researchers gathered more than 3.4 million Facebook messages and more than 140,000 images posted by 223 participants recruited for the study by Northwell.
The group of study participants ranged in age from 15 to 35 and included 79 patients with a schizophrenia spectrum disorder, 74 with a mood disorder and 70 healthy volunteers.
“There is great promise in the current research regarding the relationship between social media activity and behavioral health, and our results published with IBM Research demonstrate that machine learning algorithms are capable of identifying signals associated with mental illness, well over a year in advance of the first psychiatric hospitalization,” said Michael Birnbaum, program director for Northwell Health’s Early Treatment Program, a chief author of the study.
“We have the potential to thoughtfully bring psychiatry into the modern, digital age by integrating these data into the field.”
Birnbaum, a child psychiatrist, noted that mental disorders often happen gradually over a number of years, so analysis of social media messages and postings can help with early detection and improve treatment.
“Early identification is one of the biggest challenges in psychiatry,” he told The Post in a Sunday interview.
“You can use this information to identify risk factors. It provides additional clues.”
Down the road, such sophisticated analytics can be used to help identify warnings for suicide and other forms of violence.
“There are people we see in psychiatric clinics who we are concerned might do something dangerous,” he said.
Conversely, Birnbaum said, reviewing FB instant messages can also provide valuable insight on whether a patient is improving, as “socialization is a critical part of recovery.”
Birnbaum emphasized that using the new analytics while respecting privacy of patients will be crucial. The goal is getting patients’ consent to providing access to their digital footprint.
“The question is, how do we implement this program in a real-world setting,” he said.
The post Facebook postings help detect psychiatric illness, study finds appeared first on New York Post.