Tool-supported customization of UML class diagrams for learning complex system models

To employ an existing software library, its structure should be first learned and the required elements should be identified. This can be challenging if the library is large and only a specific part of it should be comprehended. In this paper, we study the problem of learning complex software libraries modeled in UML. It is argued that the learning process can be supported with a tool environment that allows the customization of the UML model according to the context of the learner, stepwise and dynamically chosen learning tasks, and focusing on a particular learning concern at a time. We show how such an environment can be achieved based on the concept of a pattern, using existing tool support. We demonstrate the idea with a part of Symbian platform architecture. The approach is evaluated in a case study where a pattern-driven learning environment is constructed for JPEG interchange file format specifications.