Facebook language predicts depression in medical records

TLDR

Depression is disabling, treatable, yet often underdiagnosed. The study demonstrates that Facebook posts by consenting users can predict future depression diagnoses in medical records. Analysis of Facebook language referencing typical depressive symptoms—such as sadness, loneliness, hostility, rumination, and self‑reference—shows it can predict future depression and may help clinicians identify specific symptoms.

Abstract

Significance Depression is disabling and treatable, but underdiagnosed. In this study, we show that the content shared by consenting users on Facebook can predict a future occurrence of depression in their medical records. Language predictive of depression includes references to typical symptoms, including sadness, loneliness, hostility, rumination, and increased self-reference. This study suggests that an analysis of social media data could be used to screen consenting individuals for depression. Further, social media content may point clinicians to specific symptoms of depression.