Instagram posts can reveal depression better than anything patients tell their doctors

Ellen Mills
August 9, 2017

The analysis showed a greater success rate for depression diagnosis.

The differences between mentally healthy and depressed people were tracked down to the filters on Instagram. Half of the participants had been diagnosed with depression within the past three years.

Although 71 of the study participants went on to receive a clinical diagnosis of depression, it's important to note that the researchers' computer program is not a diagnostic tool.

That matches the research that has linked depression to reduced social interaction. Analyzing factors such as hue, the use of filters and the presence of people, researchers were able to determine what they call "depression markers".

Depressed people were also less likely to use Instagram filters, and when they did, they tended to favour the Inkwell filter, which turns photos into black-and-whites.

Prof Danforth and United States colleague Andrew Reece from Harvard University wrote in a blog post accompanying the study: 'Pixel analysis of the photos in our dataset revealed that depressed individuals in our sample tended to post photos that were, on average, bluer, darker, and greyer than those posted by healthy individuals'.

Danforth said in a statement that while we tend to know our friends better than a computer could, "you might not, as a person casually flipping through Instagram, be as good at detecting depression as you think".

Unsurprisingly, "In studies associating mood, color, and mental health, healthy individuals identified darker, grayer colors with negative mood, and generally preferred brighter, more vivid colors".

The investigators then evaluated the photos using software programmed to look for known visual signs of depression. Pixel analysis of the photos in our dataset revealed that depressed individuals in our sample tended to post photos that were, on average, bluer, darker, and grayer than those posted by healthy individuals.

The methodology used meant that people with depression were correctly identified 70 percent of the time.

The study, published in the journal of EPJ Data Science, found that pictures posted by depressed social media users were also more likely to contain faces, but less likely to have a filter applied.

He also believes that this kind of application can in future help people during the onset of mental illness, avoid wrong diagnoses, and provide a new cost-efficient test for mental health services. Ideally, Danforth says the best outcome of technology like this is getting those individuals the medical support that they need. "But it is a proof of concept of a new way to help people", Danforth said.

"We were looking for subtle patterns associated with depression, and that required sifting through a lot of data to be confident about what we were seeing", Reece said.

EJP Data Science examined 166 people and 43,950 posts before making conclusions, though it claims the results are overwhelming.

Other reports by VideoGamingPros

Discuss This Article