Use this model to detect Twitter users' profiles related to healthcare. User profile classification may be useful when searching for health information on Twitter. For a certain health topic, tweets from physicians or organizations (e.g. Board-certified dermatologist) may be more reliable than undefined or vague profiles (e.g. Human. Person. Father).
The model expects the user's description text field (see Twitter API docs) as input and returns a label for each profile:
not-health-relatedhealth-relatedhealth-related/personhealth-related/organizationhealth-related/publishinghealth-related/physicianhealth-related/newshealth-related/academic
F1 score is 0.9
