Machine Learning algorithm fed by Instagram reveals predictive markers of depression
A new artificial intelligence program can pick up on the early signs of depression before humans (and even humans who are general practitioners) can — and just by using Instagram. A team of researchers from Harvard and the University of Vermont recently developed a machine learning program that correctly identified which Instagram users were clinically depressed with 70 percent accuracy.
The study by Andrew G. Reece and Christopher M. Danforth:
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 diagnostic success rate for depression. These results held even when the analysis was restricted to posts made before depressed individuals were first diagnosed. Photos posted by depressed individuals were more likely to be bluer, prayer, and darker. Human ratings of photo attributes (happy, sad, etc.) were weaker predictors of depression, and were uncorrelated with computationally generated features. These findings suggest new avenues for early screening and detection of mental illness.