@inproceedings{af8f47e72007459ab8096a44b9dbc265,
title = "TA-RE: An exchange language for mining software repositories",
abstract = "Software repositories have been getting a lot of attention from researchers in recent years. In order to analyze software repositories, it is necessary to first extract raw data from the version control and problem tracking systems. This poses two challenges: (1) extraction requires a non-trivial effort, and (2) the results depend on the heuristics used during extraction. These challenges burden researchers that are new to the community and make it difficult to benchmark software repository mining since it is almost impossible to reproduce experiments done by another team. In this paper we present the TA-RE corpus. TA-RE collects extracted data from software repositories in order to build a collection of projects that will simplify extraction process. Additionally the collection can be used for benchmarking. As the first step we propose an exchange language capable of making sharing and reusing data as simple as possible.",
keywords = "analysis, corpus, prediction, software repository mining",
author = "Sunghun Kim and Thomas Zimmermann and Miryung Kim and Ahmed Hassan and Audris Mockus and Tudor Girba and Martin Pinzger and Whitehead, \{E. James\} and Andreas Zeller",
year = "2006",
doi = "10.1145/1137983.1137990",
language = "English",
isbn = "1595933972",
series = "Proceedings - International Conference on Software Engineering",
pages = "22--25",
booktitle = "Proceedings of the 2006 International Workshop on Mining Software Repositories, MSR '06, Co-located with the 28th International Conference on Software Engineering, ICSE 2006",
note = "2006 International Workshop on Mining Software Repositories, MSR '06, Co-located with the 28th International Conference on Software Engineering, ICSE 2006 ; Conference date: 20-05-2006 Through 28-05-2006",
}