The availability of fast mobile data networks has spurred demand for more capable mobile computing devices. Conversely, the emergence of new devices has increased demand for better networks, creating an innovation cycle. Although smartphones (always-connected computing devices with multiple sensors) are less than a decade old, they will soon outnumber ``traditional'' computers, enabling data collection and analysis across a broad range of applications.
We survey the state-of-the-art in mining mobility data across different application areas, in three parts. (1) We summarize the possibilities and challenges in data collection from various sensing modalities. (2) We outline cross-cutting algorithms for mobile mining, such as context-aware analytics, and resource-constrained models. (3) We focus on how these can be usefully applied to broad classes of applications, including app usage mining, mobile advertising and search. We conclude by showcasing the opportunities for new data collection techniques and mining methods, to meet the challenges and applications that are unique to the mobile arena.
This tutorial has appeared in: