Monitoring skin condition using life activities on the SNS user documents

Abstract

Social networks are not new to the IT landscape. Starting from bulletin boards and chat rooms, they have evolved to include desktop and mobile device applications such as Facebook, Twitter, and Flickr, which are used by millions of people daily. People can post diverse types of information such as what they are doing, what kind of foods they are eating, and where they are going. Some of these activities are known to have direct/indirect effect on the condition of their skin. Typical examples include lack of sleeping, excessive drinking, and persistent sunlight exposure. In this paper, we propose a scheme for evaluating the condition of a user's skin based on their everyday activities collected from their postings. For such an evaluation, users should regularly send microscopic images of their skin to a server using their smartphone. Meanwhile, the server collects the user postings from their SNS and analyzes them to identify activities that might have an influence on their skin. Finally, the server provides the user with a report containing a comparison of their past and current skin conditions, a statistical summary of their occasional events collected from their SNS, and a set of advices for improving their skin condition including skin care products. We built a prototype system and performed various experiments to show the effectiveness of our scheme. We report some of the results.