摘要：The pap er concerns e.ort estimation of software development projects, in particular, at the level of product delivery stages. It proposes a new approach to model project data to support expert-supervised analogy-based e.ort estimation. The data is modeled using Semantic Web technologies, such as Resource Description Framework (RDF) and Ontology Language for the Web (OWL). Moreover, in the paper, we define a method of supervised case-based reasoning. The method enables to search for similar projects' tasks at di.erent levels of abstraction. For instance, instead of searching for a task performed by a specific person, one could lo ok for tasks performed by p eople with similar capabilities. The proposed method relies on ontology that defines the core concepts and relationships. However, it is possible to introduce new classes and relationships, without the need of altering the search mechanisms. Finally, we implemented a prototype tool that was used to preliminary validate the proposed approach. We observed that the proposed approach could potentially help experts in estimating non-trivial tasks that are often underestimated.
