# How an Algorithm Learned to Identify Depressed Individuals by Studying Their Instagram

**URL:** <https://boards.straightdope.com/t/how-an-algorithm-learned-to-identify-depressed-individuals-by-studying-their-instagram/763729>\
**Category:** Miscellaneous and Personal Stuff I Must Share\
**Created:** [August 23, 2016, 12:10pm UTC](https://boards.straightdope.com/t/how-an-algorithm-learned-to-identify-depressed-individuals-by-studying-their-instagram/763729 "2016-08-23T12:10:40Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![WordMan](https://avatars.discourse-cdn.com/v4/letter/w/e8c25b/32.png) [@WordMan](https://boards.straightdope.com/u/WordMan)\
**Post date:** [August 23, 2016, 12:10pm UTC](https://boards.straightdope.com/t/how-an-algorithm-learned-to-identify-depressed-individuals-by-studying-their-instagram/763729/1 "2016-08-23T12:10:40Z")

</div>

Linked to in the NYTimes, published in the MIT Tech Review: [How an Algorithm Learned to Identify Depressed Individuals by Studying Their Instagram Photos | MIT Technology Review](https://www.technologyreview.com/s/602208/how-an-algorithm-learned-to-identify-depressed-individuals-by-studying-their-instagram/)

It is what it sounds like: by statistically correlating changes in filters, color choices, subject matter, etc, a computer algorithm is being developed to be predictive for depression based on changes in a user’s social network habits.

What a Brave New World. Can I see much good from this capability? I think so, yes. Can I see Humans, being Human, using this capability in intentional and unintentional ways that lead to individual and mass-population harm? Oh, heck yes.