Demographic prediction based on user reviews about medications

Drug reactions can be extracted from user reviews provided on the Web, and processing this information in an automated way represents a novel and exciting approach to personalized medicine and wide-scale drug tests. In medical applications, demographic information regarding the authors of these reviews such as age and gender is of primary importance; however, existing studies usually assume that this information is available or overlook the issue entirely. In this work, we propose and compare several approaches to automated mining of demographic information from user-generated texts. We compare modern natural language processing techniques, including feature rich classifiers, extensions of topic models, and deep neural networks (both convolutional and recurrent architectures) for this problem