Instagram posts that reveal you have depression
Published on
20 Aug 2017
Published by
The Straits Times
The photos you share online speak volumes. They can serve as a form of self-expression or a record of travel. They can reflect your style and your quirks.
But they might convey even more than you realise - new research suggests that the photos you share may hold clues to your mental health.
From the colours and faces in their photos to the enhancements they make before posting them, Instagram users with a history of depression seem to present the world differently from their peers, according to the study, published last week in the journal EPJ Data Science.
Dr Andrew Reece, a postdoctoral researcher at Harvard University, and co-author of the study together with Professor Christopher Danforth from the University of Vermont, said: "People in our sample who were depressed tended to post photos that, on a pixel-by-pixel basis, were bluer, darker and greyer on average than healthy people."
The pair identified participants as "depressed" or "healthy", based on whether they reported having received a clinical diagnosis of depression in the past.
They used machine-learning tools to find patterns in the photos and to create a model predicting depression based on the posts.
They found that depressed participants used fewer Instagram filters, those which allow users to digitally alter brightness and colouring of a photo before it is posted.
When these users did add a filter, they tended to choose "Inkwell", which drains a photo of its colour, making it black-and-white.
The healthier users tended to prefer "Valencia", which lightens the tint of a photo.
Depressed participants were more likely to post photos containing a face. But when healthier participants did post photos with faces, theirs tended to feature more of themselves, on average.
As revealing as the findings are about Instagram posts specifically, both the study authors said that the results speak more to the promise of their techniques.
"This is only a few hundred people and they are pretty special," Prof Danforth said of the partici- pants. "There's a sieve we put them through."
Participants had to meet several criteria. They had to be active and highly rated on Amazon's Mechanical Turk platform, a paid crowdsourcing platform that researchers often use to find participants.
They also had to be active on Instagram and willing to share their entire posting history with the researchers. Finally, they had to share whether or not they had received a clinical diagnosis of depression.
Out of the hundreds of responses they received, Dr Reece and Prof Danforth recruited a total of 166 people, 71 of whom had a history of depression. They collected nearly 44,000 photos in all.
The researchers then used software to analyse the hue, colour saturation and brightness of each photo, as well as the number of faces it contained.
They also collected information about the number of posts per user and the number of comments and likes on each post.
Using machine-learning tools, they found that the more comments a post received, the more likely it was to have been posted by a depressed participant.
The opposite was true for likes.
They also found that depressed users tended to post more frequently.
Though the researchers warned that their findings may not apply to all Instagram users, they argued that the results suggest that a similar machine-learning model could in future prove useful in conducting or augmenting mental health screenings.
"We reveal a great deal about our behaviour with our activities," Prof Danforth said, "and we're a lot more predictable than we'd like to think".
NYTIMES
The Straits Times © Singapore Press Holdings Limited. Reproduced with permission.
ALL views, content, information and/or materials expressed / presented by any third party apart from Council For Third Age, belong strictly to such third party. Any such third party views, content, information and/or materials provided herein are for convenience and/or general information purposes only. Council For Third Age shall not be responsible nor liable for any injury, loss or damage whatsoever arising directly or indirectly howsoever in connection with or as a result of any person accessing or acting on any such views, content, information and/or materials. Such third party views, content, information and/or materials do not imply and shall not be construed as a representation, warranty, endorsement and/or verification by Council For Third Age in respect of such views, content, information and/or materials.
