Natural Language Processing for Productivity Metrics for Software Development Profiling in Enterprise Applications

Abstract

In this paper, we utilize ontology-based information extraction for semantic analysis and terminology linking from a corpus of software requirement specification documents from 400 enterprise-level software development projects. The purpose for this ontology is to perform semi-supervised learning on enterprise-level specification documents towards an automated method of defining productivity metrics for software development profiling. Profiling an enterprise-level software development project in the context of productivity is necessary in order to objectively measure productivity of a software development project and to identify areas of improvement in software development when compared to similar software development profiles or benchmark of these profiles. We developed a semi-novel methodology of applying NLP OBIE techniques towards determining software development productivity metrics, and evaluated this methodology on multiple practical enterprise-level software projects.