In a recent study, researchers say that Instagram photos can help predict who might have depression.
Advertisement
43,950 posts on the social media site were analysed for the study using colour analysis, metadata components and algorithmic face detection.
“We’d like the emphasis to be more on the fact that this [is] a new way of thinking about improving early detection of mental illness, than on the possibility that this early groundwork is already outperforming trained medical professionals”, Andrew Reece, a doctoral candidate at Harvard University and the study’s first author, told FoxNews.com in an email.
While other studies have shown how written information from social media can be used to predict psychiatric disorders, the group says that earlier research failed to incorporate visual posts.
Could a computer be better at identifying depression than a primary care physician? It seems that users suffering from depression have lesser social activity, even on social networks.
Depressed participants were more likely to ‘Gram photos with faces, but usually of just one or two people – so, more selfies or photos of individuals, and fewer shots with large groups.
Perhaps heralding a time yet to come, the study also found that the program was much more effective than humans who analysed the photos. Apparently people who feel depressed tend to lean more towards bluer, grayer, and darker tones, with filters like Inkwell and Crema being used the most. Depressed users are more likely to filter out colours from photos, and to include more blues and greys.
The participants’ depiction of happiness and sadness of the photos often matched whether the user suffered from depression, but when it came to interestingness and likability there were some unexpected revelations. The team asked Mechanical Turk workers to rate how likable, happy, interested and sad images were.
The researchers also took the same machine learning program and applied it to only the posts that were dated before the individual was diagnosed.
Advertisement
A second method was employed, in which a computer program analyzed pictures based on the number of faces in each photo, vividness, brightness and colourisation to decipher what qualities would be found in images posted by depressed individuals.
