Learn More
We linked names and contact information to publicly available profiles in the Personal Genome Project. These profiles contain medical and genomic information, including details about medications, procedures and diseases, and demographic information, such as date of birth, gender, and postal code. By linking demographics to public records such as voter(More)
We appreciate the opportunity to comment on the proposed rule for the electronic submission of workplace injury and illness records that appeared in 78 Federal Register 67254 (November 8, 2013). These comments address the privacy risks associated with the proposed public disclosure of such records. Our perspective is informed by substantial advances in(More)
In our final project, we took on the challenge of cross-domain classification–the adaptation of a model suitable for one domain to one or more different domains with identical features. Specifically, we developed a cross-domain classification schema to predict product categories in tweets and eBay reviews based on user reviews from Amazon. We first(More)
  • 1