International Business Machines Corporation
Multi-level machine learning to detect a social media user's possible health issue

Abstract:

Techniques for detecting a possible health issue in a user are described. Data related to social media activity for a user is received over a communications network from one or more computing devices. A user analysis profile is generated for the user using a first machine learning model. The user analysis profile includes a personality profile and a mood score. A weighted score associated with potential health issues for the user is determined by classifying the user analysis profile using a second machine learning model. The weighted score exceeds a pre-determined threshold, and electronic notification is provided to a pre-designated person regarding the potential health issue.