Classifying Venue Categories of Unlabeled Check-ins Using Mobility Patterns

摘要

Some location-based social networks (LBSNs) provide, besides other spatiotemporal data, the category of venues where the data was shared from. This information allows a wide range of semantic analyses which are very useful to understand city dynamics and urban social behavior. Despite being strategic to the study of cities and societies, some LBSNs do not offer the category of venues by default. In this study, we propose an approach to identify the category of venues of unlabeled check-ins according to their geographic locations. This new classification approach is inspired by the classic k-nearest neighbor algorithm improved by mobility pattern information captured through the user's transition information observed in LBSN data. The performance evaluation of the proposed approach is performed with real-world data from different cities: London, New York City, and Tokyo. Experiments show that, for all cities, we can achieve better performances when users' mobility is taken into account. Besides, we have an indication that transfer learning regarding mobility patterns could be feasible between similar cities.