How Facebook posts can help diagnose depression

PeoPle at risk of depression can be spotted by the language they use on Facebook and other social media sites, a study found.

Artificial intelligence predicts future depression as early as three months before symptoms emerge through markers of ‘sadness and rumination’ in online posts.

An algorithm scans social media and pinpoints ‘depression-associated language markers’ by analysing users’ most frequently used words and phrases.

Indicators of the condition included mentions of hostility and loneliness, words such as ‘tears’ and ‘feelings’, and use of more firstperson pronouns such as ‘I’ and ‘me’.

The study – at the World Well-Being Project (WWBP) based at the University of Pennsylvania – could prove important as depression affects more than a tenth of Britons aged 18 to 65 but many suffer in silence.

Senior author Andrew Schwartz said: ‘What people write in social media captures an aspect of life that’s very hard in medicine and research to access otherwise. Considering conditions such as depression, anxiety and PTSD, for example, you find more signals in the way people express themselves digitally.’

The research, published in the journal Proceedings of the National Academy of Sciences, scanned nearly 525,000 Facebook updates of 683 people. A sixth had depression and analysis showed they had used a greater amount of ‘red flag’ language in the years leading to diagnosis.

Johannes eichstaedt, WWBP founding research scientist, said: ‘Depression appears quite detectable in this way. It really changes people’s use of social media. The hope is that one day, these screening systems can be integrated into systems of care’.