Crowdsourcing Health Labels: Inferring Body Weight from Profile Pictures
This addresses the challenge of identifying chronic health conditions like obesity for public health studies, though it is incremental as it applies existing methods to a new data source.
The paper tackled the problem of detecting obesity labels from social media by inferring body weight from profile pictures, showing it is feasible and that the fraction of labeled overweight users correlates with higher obesity rates in U.S. counties, with concrete findings such as overweight users having fewer followers.
To use social media for health-related analysis, one key step is the detection of health-related labels for users. But unlike transient conditions like flu, social media users are less vocal about chronic conditions such as obesity, as users might not tweet "I'm still overweight". As, however, obesity-related conditions such as diabetes, heart disease, osteoarthritis, and even cancer are on the rise, this obese-or-not label could be one of the most useful for studies in public health. In this paper we investigate the feasibility of using profile pictures to infer if a user is overweight or not. We show that this is indeed possible and further show that the fraction of labeled-as-overweight users is higher in U.S. counties with higher obesity rates. Going from public to individual health analysis, we then find differences both in behavior and social networks, for example finding users labeled as overweight to have fewer followers.