A semantic relatedness approach for traceability link recovery

Anas Mahmoud, Nan Niu, Songhua Xu
2012 2012 20th IEEE International Conference on Program Comprehension (ICPC)  
Human analysts working with automated tracing tools need to directly vet candidate traceability links in order to determine the true traceability information. Currently, human intervention happens at the end of the traceability process, after candidate traceability links have already been generated. This often leads to a decline in the results' accuracy. In this paper, we propose an approach, based on semantic relatedness (SR), which brings human judgment to an earlier stage of the tracing
more » ... ss by integrating it into the underlying retrieval mechanism. SR tries to mimic human mental model of relevance by considering a broad range of semantic relations, hence producing more semantically meaningful results. We evaluated our approach using three datasets from different application domains, and assessed the tracing results via six different performance measures concerning both result quality and browsability. The empirical evaluation results show that our SR approach achieves a significantly better performance in recovering true links than a standard Vector Space Model (VSM) in all datasets. Our approach also achieves a significantly better precision than Latent Semantic Indexing (LSI) in two of our datasets. Index Terms-information search and retrieval, automated tracing, semantic relatedness, experimentation.
doi:10.1109/icpc.2012.6240487 dblp:conf/iwpc/MahmoudNX12 fatcat:rw6hkt3ubzdvvfdt7bysmq6zdq