However, people are revealing quite a lot with their photo manipulations posted on Instagram. Even if they're trying to conceal things. Including depression.
Andrew G. Reece and Christopher M. Danforth examined Instagram data from 166 individuals, as well as asking whether or not they had a diagnosis of clinical depression from a mental health professional. Then, they applied machine learning tools to identify markers of depression. The researchers examined 43,950 participant Instagram photos using color analysis, metadata components, and algorithmic face detection.
The results conclude that photos posted by depressed people were bluer, grayer, and darker. Also, these folks were less likely to use filters. However, when they did use photo editing tools, their most popular filter choice was Inkwell, which makes everything black and white. Interestingly, when the machine gave a depression marker, it was right about 54 percent of the time. For comparison, unassisted primary physicians correctly make a depression diagnosis about 42 percent of the time.
