As neighborhood and city exploration is one of the major themes in many location-based social network services, it is vital to provide Point-of-Interest (POI) recommendations to users. With a fast growing number of mobile users and POIs within such services, it is important to adopt efficient techniques so as to provide precise POI recommendations. Owing to the strong participation of knowledgeable users, a social networking service can be seen as a large number of experts who support the decisions of online users. People make decisions based on their personal preferences, but they also rely strongly on the opinions of others, especially close friends or influential people. The “location” where the decision-making takes place is also equally important in affecting user behaviour. In this paper, we propose a social decision support mechanism that integrates the methodologies and techniques of social network analysis, geographic distance analysis, and local expert analysis to achieve social decision support for mobile users. We aim to discover the POIs to which a mobile user is likely to go. With this proposed mechanism, online users can efficiently reduce their decision-making processes and reduce the risk of visiting an unsuitable POI.