@conference {herraiz2009research, title = {Research friendly software repositories}, booktitle = {Proceedings of the joint international and annual ERCIM workshops on Principles of software evolution (IWPSE) and software evolution (Evol) workshops}, year = {2009}, note = {"In spite of these rich availability of software repositories, the heterogeneity of the data makes it difficult to apply studies at a large scale, although some research projects, like FLOSSMole [10] or FLOSSMetrics [8] are addressing these issues and aim to provide datasets about thousands of libre software projects for research purposes." (more)}, pages = {19{\textendash}24}, publisher = {ACM}, organization = {ACM}, abstract = {What is the future of software evolution? In 1974, Meir M. Lehman had a vision of software evolution being driven by empirical studies of software repositories, and of a theory based on those empirical results. However, that scenario is yet to come. Software evolution studies are often based on a few cases, because the needed information is scarce, dispersed and incomplete. Their conclusions are not generalizable, slowing down the progress of this research discipline. Libre (free / open source) software supposes an opportunity to alleviate this situation. In this paper we describe the existing approaches to provide research datasets that are mining libre software repositories, and propose an agenda based on the concept of research friendly software repositories, which provides finer granularity and integrated data.}, keywords = {flossmetrics, flossmole cited}, attachments = {https://flosshub.org/sites/flosshub.org/files/herraiz-Research-Friendly-sw-repos.pdf}, author = {Herraiz, I. and Robles, G. and Gonzalez-Barahona, J.M.} } @article {120, title = {Applying Social Network Analysis Techniques to Community-Driven Libre Software Projects}, journal = {International Journal of Information Technology and Web Engineering}, volume = {1}, number = {3}, year = {2006}, abstract = {Source code management repositories of large, long-lived libre (free, open source) software projects can be a source of valuable data about the organizational structure, evolution, and knowledge exchange in the corresponding development communities. Unfortunately, the sheer volume of the available information renders it almost unusable without applying methodologies which highlight the relevant information for a given aspect of the project. Such methodology is proposed in this article, based on well known concepts from the social networks analysis field, which can be used to study the relationships among developers and how they collaborate in different parts of a project. It is also applied to data mined from some well known projects (Apache, GNOME, and KDE), focusing on the characterization of their collaboration network architecture. These cases help to understand the potentials of the methodology and how it is applied, but also shows some relevant results which open new paths in the understanding of the informal organization of libre software development communities.}, keywords = {apache, conway{\textquoteright}s law, cvs, gnome, kde, scm, social network analysis, source code}, attachments = {https://flosshub.org/sites/flosshub.org/files/06_Lopez_ijitwe_sna.pdf}, author = {L{\'o}pez-Fern{\'a}ndez, L. and Gregorio Robles and Jesus M. Gonzalez-Barahona and Herraiz, I.} } @article {130, title = {Evolution and growth in large libre software projects}, journal = {Principles of Software Evolution, Eighth International Workshop on}, year = {2005}, pages = {165-174}, author = {Gregorio Robles and Amor, J. J. and Jesus M. Gonzalez-Barahona and Herraiz, I.} }