Facebook successfully picks depressed patients
Use of more first-person pronouns were one of the indicators
18th October 2018
Facebook posts and status updates may reveal more about patients than simply their latest travel destinations.

By analysing language used on social media, researchers created an algorithm that could predict which users would be diagnosed with depression — three months ahead of their diagnosis.
Mentions of hostility and loneliness, words like "tears" and "feelings", and use of more first-person pronouns were found to be indicators of the condition.
The accuracy of linguistic red flags