Instagram photos reveal predictive markers of depression

Article, Preprint English OPEN
Reece, Andrew G.; Danforth, Christopher M.;
  • Publisher: SpringerOpen
  • Journal: EPJ Data Science (issn: 2193-1127)
  • Publisher copyright policies & self-archiving
  • Identifiers: doi: 10.1140/epjds/s13688-017-0110-z
  • Subject: R858-859.7 | Computer applications to medicine. Medical informatics | Computer Science - Social and Information Networks | psychology | Physics - Physics and Society | depression | machine learning | social media | computational social science

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 algo... View more
Share - Bookmark