The widespread usage of Internet-connected mobile devices allows users’ behavior to be recorded in large-scale and fine-grained digital traces. Such data, termed mobile big data, contain great social, economic, and academic values. Analyzing mobile big data has significant implications for all relevant stakeholders, ranging from smartphone manufacturers, network operators to app developers.

This thesis aims to discover and understand behavioral patterns from mobile big data based on large-scale and real-world datasets. Specifically, this thesis reveals behavioral patterns from three scales, i.e., short-term patterns, long-term patterns, and disrupted patterns. Firstly, we explore short-term temporal patterns and propose a framework to discover users’ daily activity patterns from their m...[ Read more ]

The widespread usage of Internet-connected mobile devices allows users’ behavior to be recorded in large-scale and fine-grained digital traces. Such data, termed mobile big data, contain great social, economic, and academic values. Analyzing mobile big data has significant implications for all relevant stakeholders, ranging from smartphone manufacturers, network operators to app developers.

This thesis aims to discover and understand behavioral patterns from mobile big data based on large-scale and real-world datasets. Specifically, this thesis reveals behavioral patterns from three scales, i.e., short-term patterns, long-term patterns, and disrupted patterns. Firstly, we explore short-term temporal patterns and propose a framework to discover users’ daily activity patterns from their mobile app usage. By applying the framework to a real-world dataset consisting of 653,092 users, we successfully extract five common patterns among millions of people, including commuting, pervasive socializing, nightly entertainment, afternoon reading, and nightly socializing. Secondly, we leverage short-term spatiotemporal mobile usage patterns to reveal urban dynamics. We prove the strong correlation between mobile usage behavior and location features, which brings a new angle to urban analytics. Thirdly, we mine the behavior patterns from the long-term scale. We reveal the longitudinal evolution of mobile app usage by conducting a study on 1,465 users from 2012 to 2017. The results show that users’ app usage evolves over time. However, the evolutionary processes in app-category usage and individual app usage are different in terms of popularity distribution, usage diversity, and correlations. Lastly, we study how the behavioral patterns were disrupted through extreme global events, i.e., the pandemic of Covid-19. We collect mobile usage records of 452 users in North America. We then manifest the potential for inferring Covid-19 outbreak stages by leveraging disrupted mobile usage patterns. In the end, we conclude this thesis with future research directions and challenges related to mobile big data analysis.