Another week, another social media study. But this particular one looks at the usefulness of social media activity as a diagnostic tool within psychology: a computer programme developed by researchers in Harvard and the University of Vermont has been found to be 70 per cent accurate in detecting signs of depression by analysing images posted on Instagram.

The study recruited 166 Instagram users (71 of which were diagnosed with clinical depression) and analysed 43,950 photos in total. The programme linked certain photo details to healthy or depressed individuals and, using machine learning, built a predictive model for assessing people prior to a clinical diagnosis.

Dr Christopher Danforth, study co-author from the University of Vermont, said that photos posted by people diagnosed with depression "tended to be darker in colour, received more comments from the community, were more likely to contain faces and less likely to have a filter applied". Depressed individuals also tended to post more frequently.

epjdatascience.springeropen.com/articles/10.1140/epjds/s13688-017-0110-z