Assessing Word Similarity Metrics For Traceability Link Recovery

Aus SDQ-Institutsseminar
Vortragende(r) Kevin Werber
Vortragstyp Bachelorarbeit
Betreuer(in) Jan Keim
Termin Fr 24. Juni 2022
Vortragsmodus online
Kurzfassung The software development process usually involves different artifacts that each describe different parts of the whole software system. Traceability Link Recovery is a technique that aids the development process by establishing relationships between related parts from different artifacts. Artifacts that are expressed in natural language are more difficult for machines to understand and therefore pose a challenge to this link recovery process. A common approach to link elements from different artifacts is to identify similar words using word similarity measures. ArDoCo is a tool that uses word similarity measures to recover trace links between natural language software architecture documentation and formal architectural models. This thesis assesses the effect of different word similarity measures on ArDoCo. The measures are evaluated using multiple case studies. Precision, recall, and encountered challenges for the different measures are reported as part of the evaluation.