Abstract. Within the last years, an ever increasing amount of data from mobile and navigation devices (e.g. web check-in, vehicle tracking data, etc), as well as social media (e.g. Twitter) are becoming available, presenting and enabling new research challenges and applications. To unveil persistent and meaningful knowledge from user-generated location-based “stories”, this work proposes a novel methodology that converts Twitter check-in data into a mixed geo-semantic network-of-interest (NOI). It does so by introducing a novel network construction algorithm on segmented input data based on different mobility types. This produces network layers by means of behavioral and geometric trajectories, which are then combined into a single network. This segmentation addresses also the challenges imposed by noisy, low-sampling rate trajectories. An experimental evaluation assesses the quality of the algorithms by constructing the a network from trajectories based on Twitter check-in data for London and New York. Our results show that this method is robust and provides accurate and interesting results.