Topic cohesion preserving requirements clustering

Abstract

This paper focuses on the problem of generating human interpretable clusters of semantically related plain-text requirements. Presented approach applies techniques from information retrieval, natural language processing, network analysis, and machine learning for identifying semantically central terms as themes and clustering requirements into semantically coherent groups together with meaningful explanatory themes associated with the clusters to assist in user comprehension of the clusters. Presented approach is generic in nature and can be used for other phases of SDLC (Software Development Life Cycle) including code-comprehension and architectural discovery. Suggested approach is particularly suitable for developing automated tool support for requirements management and analysis.