Towards comprehensive repositories of opinions

Despite the popularity of recommendation services (such as Yelp, Healthgrades, and Angie's List), for a majority of entities listed on these services, one has to rely on opinions shared by a few users. We argue that this paucity of reviews for most entities stems from the fact that the vast majority of users largely consume opinions shared by others but seldom post reviews themselves. Therefore, leveraging the trend that services are increasingly accessed from a clientside app rather than over the Web, we propose augmenting recommendation services to implicitly infer any user's opinions based on observations of the user's activities. Implicit inference of many of a user's recommendations are feasible due to the rich sensory capabilities of smartphones and wearables as well as the digital footprints left behind by many activities in the physical world. However, implicit inference of opinions is inherently uncertain and automated sharing of inferences raises significant privacy and security concerns. In this paper, we discuss how to tackle these challenges so that users looking for recommendations can draw upon a more comprehensive set of opinions than is the case today.