Exploiting SequentialMobility for Recommending new Locations on Geo-tagged Social Media

Social media represent one of the main sources of information concerning human dynamics within an urban context, allowing to enhance the comprehension of people behaviour, including human mobility regularities. The paper presents an approach to recommend new unseen locations to social media users exploiting historic mobility data, social features of users and geographic characteristics of locations. The location recommendation problem is formulated as a ranking task so that the recommended locations will be ranked at the highest position in the prediction set. A ranking function that exploits users' similarity in visiting locations and in travelling along mobility paths is proposed to predict places the user could like. The experimental results obtained by using a real-world dataset of tweets show that the proposed method is effective in recommending unseen locations, achieving remarkable precision and recall rates.