Supplementary Material of "Requirements Classification for Traceability Link Recovery"

This repository includes further results as well as the source code of the paper "Requirements Classification for Traceability Link Recovery".

• results.xlsx contains further classification results
• results_TLR_comparison.csv contains further metrics for the comparison to state-of-the-art in Traceability Link Recovery
• The folder NoRBERT_for_TLR contains the source code for classifying the TLR datasets with NoRBERT
• The folder FTLR_Adaptation contains an adapted version of FTLR that can use both automatic, and gold standard classification results during preprocessing

Further information on how to run the code can be found in the README files in the respective folders.

For docker images to run the tools, please refer to these two repositories: FTLR,  NoRBERT_for_TLR

Attribution (of datasets used):

The original SMOS and eAnci dataset can be attributed to Gethers et al., On integrating orthogonal information retrieval methods to improve traceability recovery. In 2011 27th IEEE International Conference on Software Maintenance (ICSM), Sep. 2011. Available: https://doi.org/10.1109/ICSM.2011.6080780

The original eTour dataset was provided for the TEFSE challenge at 6th International Workshop on Traceability in Emerging Forms of Software Engineering (TEFSE), 2011 and was retrieved from http://coest.org/

The iTrust dataset was retrieved from http://coest.org/

The LibEST dataset can be attributed to Moran et al., Improving the Effectiveness of Traceability Link Recovery using Hierarchical Bayesian Networks. In 2020 IEEE/ACM 42nd International Conference on Software Engineering (ICSE), May 2020 and was retrieved from https://gitlab.com/SEMERU-Code-Public/Data/icse20-comet-data-replication-package

The Albergate dataset can be attributed to Antoniol et al., Recovering traceability links between code and documentation. In IEEE Trans. on Software Eng., 28(10):970–983, 2002 and was retrieved from http://coest.org/