They say a picture tells a thousand words, and while a thousand might be pushing it a little, a new study has revealed there could be some truth behind the well-known proverb.

Scientists have developed an algorithm that can determine whether or not an Instagram user is showing signs of depression based on their posts.

According to the study, published by EPJ Data Science, researchers from Harvard University and the University of Vermont assessed just under 44,000 photos from 166 users – 71 of which had a history of depression.

Using insights form previous psychological studies, the photos were then examined on their colour schemes, the number of faces and the number of likes received.

Results showed that people who were depressed tended to post photos and opt for filters that were darker in tone.

The specially designed algorithm was able to successfully identify signs of depression 70 per cent of the time.

What's more, it was able to spot these signs before participants were clinically diagnosed.

However, authors of the study have warned that the research was limited by the relatively small sample size and said that while the findings cannot be applied to every Instagram user, they do provide a "blueprint for effective mental health screening in an increasingly digitalized society."