We perform an empirical study to understand the interaction between IR-based similarity measures and document types, and observed that model choice has a significant impact on performance for the different types of artifacts. In a case study on two SE tasks, we found that such informed choice of similarity measure indeed leads to improved performance of the SE tools.
. A Case Study on the Impact of Similarity Measure on Information Retrieval based Software Engineering Tasks. Md Masudur Rahman, Saikat Chakraborty, Gail Kaiser, Baishakhi Ray. Technical Reports. [ArXiv] [Arxiv PDF]
. Which Similarity Metric to Use for Software Documents? A study on Information Retrieval based Software Engineering Tasks. Md Masudur Rahman, Saikat Chakraborty, Baishakhi Ray. In Proceedings of 40th International Conference on Software Engineering Companion, Gothenburg, Sweden, May 27-June 3, 2018 (ICSE ’18 Companion), 2 pages. [DOI]