Quantitative Analysis of Community Detection Methods for Longitudinal Mobile Data

Mobile phones are now equipped with increasingly large number of built-in sensors that can be utilized to collect long-term socio-temporal data of social interactions. Moreover, the data from different built-in sensors can be combined to predict social interactions. In this paper, we perform quantitative analysis of 6 community detection algorithms to uncover the community structure from the mobile data. We use Bluetooth, WLAN, GPS, and contact data for analysis, where each modality is modelled as an undirected weighted graph. We evaluate community detection algorithms across 6 inter-modality pairs, and use well know partition evaluation features to measure clustering similarity between the pairs. We compare the performance of different methods based on the delivered partitions, and analyse the graphs at different times to find out the community stability.