Prospects and Challenges of Deep Understanding Social Users and Urban Services - a position paper

With the boom of social media, it is a very popular trend for people to share their consumption experiences and rate the items on the review site. Users can share their experiences, reviews, ratings, photos, check-ins, moods, and so on. The information they shared is valuable for new users to judge whether the items have high-quality services. Nowadays, many researchers focus on personalized recommendation and rating prediction. They miss the significance of service objective evaluation. We can find the evaluations of services from large users by their ratings and comments. The more user ratings, the more easily we obtain the objective evaluation. But how does it work for new items? It is lack of objectivity if there are few users have rated the item, such as there are just two ratings. In this paper, we discuss the prospects and challenges of deep understanding social users and urban services, and propose some key problems for research by making full using of the big urban data generated by social users, including user rating behavior study, user sentiment study, spatial-temporal features study, and user social circle study. We focus on exploring user ratings confidence, which we propose to denote the trustworthiness of user ratings for service objective evaluation by deep understanding social users and urban services. We conduct some preliminary statistical analysis to demonstrate that these studies are necessary and potential for urban service objective evaluation.