Context aware functionalities are functionalities that consider context to produce a certain system behavior, typically an adaptation or recommendation. From a requirements engineering viewpoint, building a context-aware system calls for context modeling, an early step that comprises a set of activities responsible for understanding what the context is for the application domain, and how the context influences user tasks of interest. As a result, a context model is created and is expected to support requirement engineers in identifying new context-aware functionalities to improve these user tasks. In practice, however, context modeling activities have been disregarded due to their high complexity. As a consequence, contexts are created where only few contextual elements are combined, which leads to opportunities for discovering unexpected context-aware functionalities being missed. In this thesis, this problem is addressed by using a data-driven approach to analyze contextual data and automate context modeling. For this purpose, a data-driven context modeling framework has been developed to support the elicitation of context-aware functionalities.