Feeling blue can unconsciously colour the photos you share online, a new study has suggested.
It found that people suffering from depression were more likely to choose darker and blue-tinted filters for their images on Instagram.
Computer analysis of social media posts was more accurate than humans in identifying people in distress, said the US scientists behind the study.
It could also spot signs of depression in images shared even before their illness was diagnosed by doctors, they said.
The study analysed a total of 43,950 photographs shared on Instagram by 166 people who volunteered to take part.
Participants also agreed to disclose details of their mental health history, with around half saying they had suffered clinical depression within the last three years.
Scientists found that people with good mental health tended to favour bright Instagram filters such as Valencia.
Meanwhile, the top filter chosen by those suffering from depression was Inkwell, which turns photographs black and white.
Academics at the University of Vermont and Harvard University said that they were able to identify people with depression with 70% accuracy through the analysis of their social media posts.
That compares to a successful diagnosis rate of depression by GPs of just 42%, they added.
Study co-leader Professor Chris Danforth, from the University of Vermont, suggested that the analysis could help to identify people with depression earlier and with greater accuracy in future.
He said it could potentially be used as part of screening for early signs of mental illness or help to confirm a diagnosis of depression.
Chloe Grass-Orkin, from the charity Rethink Mental Illness, said the study offered could offer new prospects to identify people in need of support.
She said: "For many people, using social media is now second nature and forms a part of our daily lives, so being able to integrate mental health support within these platforms offers exciting possibilities.
"This is clearly a new frontier for research. Developments and improvements in the recognition of mental health problems, and helping people access appropriate care and support, are very much needed.
"However, it is still very early days, and care must be taken not to jump to conclusions or oversimplify and reduce diagnosis to someone's social media footprint.