Regular article

Instagram photos reveal predictive markers of depression

¹ Department of Psychology, Harvard University, 33 Kirkland St, Cambridge, MA, 02138, USA
² Computational Story Lab, Vermont Advanced Computing Core, University of Vermont, 210 Colchester Ave, Burlington, VT, 05405, USA
³ Department of Mathematics and Statistics, University of Vermont, 210 Colchester Ave, Burlington, VT, 05405, USA
⁴ Vermont Complex Systems Center, University of Vermont, 210 Colchester Ave, Burlington, VT, 05405, USA

^* e-mail: reece@g.harvard.edu
^** e-mail: chris.danforth@uvm.edu

Received: 28 March 2017
Accepted: 22 June 2017
Published online: 8 August 2017

Abstract

Using Instagram data from 166 individuals, we applied machine learning tools to successfully identify markers of depression. Statistical features were computationally extracted from 43,950 participant Instagram photos, using color analysis, metadata components, and algorithmic face detection. Resulting models outperformed general practitioners’ average unassisted diagnostic success rate for depression. These results held even when the analysis was restricted to posts made before depressed individuals were first diagnosed. Human ratings of photo attributes (happy, sad, etc.) were weaker predictors of depression, and were uncorrelated with computationally-generated features. These results suggest new avenues for early screening and detection of mental illness.