Researchers from Harvard University and University of Vermont have developed an algorithm that checks photos on Instagram to diagnose depression.
Researchers examined about 170 workers from Amazon. All participants completed a questionnaire, which included a clinical depression survey. The study categorised the photos based on saturation, hue and number of faces each picture had.
Researchers found decreased saturation and brightness, and increased hue predicted depression. Researchers also found depressed people were less likely to use filters. The algorithm had a 70% success rate.