A Knowledge Graph Construction Method for Software Project Based on CAJP

Abstract

In recent years, there has been increasing interest in using knowledge graphs (KGs) to help stakeholders organize and better understand the connections between various artifacts during software development. However, extracting entities and relationships automatically and accurately in open-source projects is still a challenge. Therefore, an efficient method called Concise Annotated JavaParser (CAJP) has been proposed to support these extraction activities, which are vitally important for KG construction. The experimental result shows that CAJP improves the accuracy and type of entity extraction and ensures the accuracy of relationship exaction. Moreover, an intelligent question-and-answer (Q&A) system is designed to visualize and verify the quality of the KGs constructed from six open-source projects. Overall, the software project-oriented KG provides developers a valuable and intuitive way to access and understand project information.