| Abstract |
Social sensing has emerged as a new application paradigm for smart cities where a crowd of social sources (humans or devices on their behalf) collectively contribute a large amount of observations about the physical world. This paper focuses on an interesting place finding problem in social sensing where the goal is to accurately identify the interesting places in a city where people may have strong interests to visit (e.g., parks, museums, historic sites, scenic trails, etc.). Solving this problem is not trivial because (i) many interesting places are not necessarily frequently visited by the average people and hence less likely to be found by the traditional recommendation systems; (ii) the user's social connections could directly affect their visiting behavior and the interestingness judgment of a given place. In this paper, we develop a new Social-aware Interesting Place Finding (SIPF) approach that solves the above problem by explicitly incorporating both the user's travel experience and social relationship into a rigorous analytical framework. The evaluation results showed that the new approach significantly outperforms the state-of-the-arts using two real-world datasets collected from location-based social network service. |
