科研成果详情

The research of collective behavior has attracted a lot of attention in recent years, which can empower various applications, such as recommendation systems and intelligent transportation systems. However, in traditional social science, it is practically difficult to collect large-scale user behavior data. Fortunately, with the ubiquity of smartphones and Location Based Social Networks (LBSNs), users continuously report their activities online, which massively reflect their collective behavior. In this paper, we propose NationTelescope, a platform that monitors, compares and visualizes large-scale nation-wide user behavior in LBSNs. First, it continuously collects user behavior data from LBSNs. Second, it automatically generates behavior data summary and integrates an interactive map interface for data visualization. Third, in order to compare and visualize the behavioral differences across countries, it detects the discriminative activities according to the related traffic patterns in different countries. By implementing a prototype of NationTelescope platform, we evaluate its effectiveness and usability via two case studies and a system usability scale survey. The results show that the platform can not only efficiently capture, compare and visualize nation-wide collective behavior, but also achieve good usability and user experience.