Mining Collaboration Patterns Of Software Development Processes Based On Trace Alignment

Developing large-scale software usually involves the interaction of a great number of engineers over a long period. To discover the collaboration patterns from developing logs helps improve the software development processes. Traditional techniques of process mining can be employed to identify such patterns. Unfortunately, due to the high uncertainty of software development process, they tend to obtain "spaghetti" models which are difficult to comprehend or even misleading. As a remedy, in this paper we propose an approach to the discovery of collaboration patterns existing in software development process by aligning development logs. It considers not only the sequence of activities, but also the collaboration of actors who perform activities. Instead of using time-consuming graph mining techniques, it employs the trace alignment, which is much more straightforward. Moreover, unlike some traditional approaches, the discovered patterns are determined because we do not depend on the mined process model that is usually uncertain due to the unstructured nature of software development process. The experimental results based on a large dataset generated from CPNTools demonstrate the effectiveness of our approach.