Requirements Traceability: Recovering and Visualizing Traceability Links Between Requirements and Source Code of Object-oriented Software Systems

TL;DR

YamenTrace is an automated tool that recovers and visualizes requirements-to-code traceability links in object-oriented software using semantic analysis and clustering, reducing manual effort and errors.

Contribution

It introduces YamenTrace, combining LSI and FCA to automatically recover and visualize traceability links leveraging code identifiers, comments, and relations.

Findings

Most RtC-TLs were correctly recovered.

YamenTrace effectively visualizes traceability links.

Validation on three case studies confirms its performance.

Abstract

Requirements traceability is an important activity to reach an effective requirements management method in the requirements engineering. Requirement-to-Code Traceability Links (RtC-TLs) shape the relations between requirement and source code artifacts. RtC-TLs can assist engineers to know which parts of software code implement a specific requirement. In addition, these links can assist engineers to keep a correct mental model of software, and decreasing the risk of code quality degradation when requirements change with time mainly in large sized and complex software. However, manually recovering and preserving of these TLs puts an additional burden on engineers and is error-prone, tedious, and costly task. This paper introduces YamenTrace, an automatic approach and implementation to recover and visualize RtC-TLs in Object-Oriented software based on Latent Semantic Indexing (LSI) and Formal Concept Analysis (FCA). The originality of YamenTrace is that it exploits all code identifier names, comments, and relations in TLs recovery process. YamenTrace uses LSI to find textual similarity across software code and requirements. While FCA employs to cluster similar code and requirements together. Furthermore, YamenTrace gives a visualization of recovered TLs. To validate YamenTrace, it applied on three case studies. The findings of this evaluation prove the importance and performance of YamenTrace proposal as most of RtC-TLs were correctly recovered and visualized.