The study found that users with confirmed depression usually posted bluer, darker, and more faded images. In fact, when creators Andrew Reece at Harvard University and Chris Danforth at the University of Vermont asked humans to judge photos as happy or sad, the human rating had a weak correlation with detecting actual depression.
Advertisement
According to the researchers, there is a connection between the usage of colour and the mental state of a person. Then researchers analyzed Instagram posts of depressed individuals to find commonalities. There’s also the issue that the volunteers were crowd-sourced through Amazon Mechanical Turk which tends to attract those with a lot of free time on their hands rather than, say, people who put in 60-hour work weeks.
I do use a filter but don’t know the names of any and couldn’t tell you what my favorite is. The immensely popular photo-sharing app recently launched a “Stories” feature.
Upon deeper research, Instagram users in the study were asked to take questionnaires and were surveyed for clinical depression.
The raters, who were independently sourced, judge the photos on how interesting, likable, happy, and sad each photo seemed on a scale of 0 to 5. The photos were also objectively categorised by hue and saturation, along with likes and the number of faces in each.
The researchers found that the most telling sign of whether or not a person was depressed was how he or she used filters. It was also able to pick out depression based on the filters that were used. For instance, the researchers found that depressed people were less likely to use filters.
The algorithm had a 70 per cent chance of finding a person with depression and the researchers said: “More generally, these findings support the notion that major changes in individual psychology are transmitted in social media use, and can be identified via computational methods”.
Several social media platforms already carry some of your most personal details that allows others to seep in to your mind and personal life. But try as we may, a new study suggests we could be subconsciously revealing a rift in this picture-perfect narrative.
The model of study also considers Instagram filters as a tool to determine your mental state.
It’s important to note that only the computer analysis proved to be successful in predicting depression among the participants of the study. Hypothesis 1: Instagram posts made by individuals diagnosed with depression can be reliably distinguished from posts made by healthy individuals, using only measures extracted computationally from posted photos and associated metadata.
Advertisement
The team hope that by using computer learning they will be able to harness social media to detect early signs of depression by creating “a blueprint for effective mental health screening in an increasingly digitalized society”.
