@conference {Matragkas:2014:ABO:2597073.2597119, title = {Analysing the {\textquoteright}Biodiversity{\textquoteright} of Open Source Ecosystems: The GitHub Case}, booktitle = {Proceedings of the 11th Working Conference on Mining Software Repositories}, series = {MSR 2014}, year = {2014}, pages = {356{\textendash}359}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {In nature the diversity of species and genes in ecological communities affects the functioning of these communities. Biologists have found out that more diverse communities appear to be more productive than less diverse communities. Moreover such communities appear to be more stable in the face of perturbations. In this paper, we draw the analogy between ecological communities and Open Source Software (OSS) ecosystems, and we investigate the diversity and structure of OSS communities. To address this question we use the MSR 2014 challenge dataset, which includes data from the top-10 software projects for the top programming languages on GitHub. Our findings show that OSS communities on GitHub consist of 3 types of users (core developers, active users, passive users). Moreover, we show that the percentage of core developers and active users does not change as the project grows and that the majority of members of large projects are passive users. }, keywords = {Data and knowledge visualization, data mining, mining challenge, msr challenge}, isbn = {978-1-4503-2863-0}, doi = {10.1145/2597073.2597119}, url = {http://doi.acm.org/10.1145/2597073.2597119}, author = {Matragkas, Nicholas and Williams, James R. and Kolovos, Dimitris S. and Paige, Richard F.} } @conference {Williams:2014:MOP:2597073.2597132, title = {Models of OSS Project Meta-information: A Dataset of Three Forges}, booktitle = {Proceedings of the 11th Working Conference on Mining Software Repositories}, series = {MSR 2014}, year = {2014}, note = {"FLOSSMole [4] is a similar initiative to OSSMETER; it aims to collect and freely redistribute in different formats the data of open source software. Differently from OSSMETER, however, the FLOSSMole project does not provide the instruments to analyse data, that are simply collected and made publicly available."}, pages = {408{\textendash}411}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {The process of selecting open-source software (OSS) for adoption is not straightforward as it involves exploring various sources of information to determine the quality, maturity, activity, and user support of each project. In the context of the OSSMETER project, we have developed a forge-agnostic metamodel that captures the meta-information common to all OSS projects. We specialise this metamodel for popular OSS forges in order to capture forge-specific meta-information. In this paper we present a dataset conforming to these metamodels for over 500,000 OSS projects hosted on three popular OSS forges: Eclipse, SourceForge, and GitHub. The dataset enables different kinds of automatic analysis and supports objective comparisons of cross-forge OSS alternatives with respect to a user{\textquoteright}s needs and quality requirements. }, keywords = {data mining, flossmole cited}, isbn = {978-1-4503-2863-0}, doi = {10.1145/2597073.2597132}, url = {http://doi.acm.org/10.1145/2597073.2597132}, attachments = {https://flosshub.org/sites/flosshub.org/files/Models_of_OSS_Project_Meta-Information_A_Dataset_of_Three_Forges_draft.pdf}, author = {Williams, James R. and Di Ruscio, Davide and Matragkas, Nicholas and Di Rocco, Juri and Kolovos, Dimitris S.} }