@proceedings {1914, title = {Practices and Perceptions of UML Use in Open Source Projects}, year = {2017}, month = {05/2017}, pages = {203-212}, abstract = {Context: Open Source is getting more and more collaborative with industry. At the same time, modeling is today playing a crucial role in development of, e.g., safety critical software. Goal: However, there is a lack of research about the use of modeling in Open Source. Our goal is to shed some light into the motivation and benefits of the use of modeling and its use within project teams. Method: In this study, we perform a survey among Open Source developers. We focus on projects that use the Unified Modeling Language (UML) as a representative for software modeling. Results: We received 485 answers of contributors of 458 different Open Source projects. Conclusion: Collaboration seems to be the most important motivation for using UML. It benefits new contributors and contributors who do not create models. Teams use UML during communication and planning of joint implementation efforts.}, keywords = {architecture documentation, communication, effectiveness of UML, github, MOTIVATION, UML}, author = {Truong Ho-Quang and Hebig, Regina and Gregorio Robles and Chaudron, Michel R. V. and Miguel Angel Fernandez} } @article {1869, title = {Predicting bug-fixing time: A replication study using an open source software project}, journal = {Journal of Systems and Software}, year = {2017}, month = {2/2017}, abstract = {Background: On projects with tight schedules and limited budgets, it may not be possible to resolve all known bugs before the next release. Estimates of the time required to fix known bugs (the {\textquotedblleft}bug fixing time{\textquotedblright}) would assist managers in allocating bug fixing resources when faced with a high volume of bug reports. Aim: In this work, we aim to replicate a model for predicting bug fixing time with open source data from Bugzilla Firefox. Method: To perform the replication study, we follow the replication guidelines put forth by Carver [J. C. Carver, Towards reporting guidelines for experimental replications: a proposal, in: 1st International Workshop on Replication in Empirical Software Engineering, 2010.]. Similar to the original study, we apply a Markov-based model to predict the number of bugs that can be fixed monthly. In addition, we employ Monte-Carlo simulation to predict the total fixing time for a given number of bugs. We then use the k-nearest neighbors algorithm to classify fixing times into slow and fast. Result: The results of the replicated study on Firefox are consistent with those of the original study. The results show that there are similarities in the bug handling behaviour of both systems. Conclusion: We conclude that the model that estimates the bug fixing time is robust enough to be generalized, and we can rely on this model for our future research.}, keywords = {Replication study; Bug fixing time; Effort estimation; Software maintainability; Deferred bugs}, issn = {01641212}, doi = {10.1016/j.jss.2017.02.021}, author = {Akbarinasaji, Shirin and Caglayan, Bora and Bener, Ayse} } @proceedings {1891, title = {Principled Evaluation of Strengths and Weaknesses in FLOSS Communities: A Systematic Mixed Methods Maturity Model Approach}, volume = {496}, year = {2017}, month = {05/2017}, pages = {34-46}, publisher = {Springer}, abstract = {Context: Free and Open Source Software usually results from intricate socio-technical dynamics operating in a diverse and geographically dispersed community. Understanding the fundamental underpinnings of healthy and thriving communities is of paramount importance to evaluate existing efforts and identify improvement opportunities. Objective: This paper presents a novel reference model for evaluating the maturity of FLOSS communities by mixing quantitative and qualitative methods. Method: We build upon established guidelines for Design Science research in order to devise a well-informed and expressive maturity model, describing how those methods and procedures were used in the design and development of such a model. Results: We present the model structure and functions, as well as instructions on how to instantiate it as evaluations of FLOSS communities. The use of the proposed maturity model is demonstrated in four FLOSS communities. Conclusion: Whilst instantiating the model may be burdensome if aiming at sketchy evaluations, results indicate our model effectively captures the maturity regardless aspects such as community size and lifetime.}, keywords = {Design science research, Discourse communities, evaluation, FLOSS communities, maturity models, Mixed methods research}, doi = {10.1007/978-3-319-57735-7_4}, url = {https://link.springer.com/chapter/10.1007/978-3-319-57735-7_4}, author = {Andrade, S and Saraiva, F.} } @article {1920, title = {Process Aspects and Social Dynamics of Contemporary Code Review: Insights from Open Source Development and Industrial Practice at Microsoft}, journal = {IEEE Transactions on Software Engineering}, volume = {43}, year = {2017}, note = {" We sent the survey to code review participants from 36 popular OSS projects and received 287 responses"}, month = {1/2017}, pages = {56 - 75}, abstract = {Many open source and commercial developers practice contemporary code review, a lightweight, informal, tool-based code review process. To better understand this process and its benefits, we gathered information about code review practices via surveys of open source software developers and developers from Microsoft. The results of our analysis suggest that developers spend approximately 10-15 percent of their time in code reviews, with the amount of effort increasing with experience. Developers consider code review important, stating that in addition to finding defects, code reviews offer other benefits, including knowledge sharing, community building, and maintaining code quality. The quality of the code submitted for review helps reviewers form impressions about their teammates, which can influence future collaborations. We found a large amount of similarity between the Microsoft and OSS respondents. One interesting difference is that while OSS respondents view code review as an important method of impression formation, Microsoft respondents found knowledge dissemination to be more important. Finally, we found little difference between distributed and co-located Microsoft teams. Our findings identify the following key areas that warrant focused research: 1) exploring the non-technical benefits of code reviews, 2) helping developers in articulating review comments, and 3) assisting reviewers{\textquoteright} program comprehension during code reviews.}, keywords = {code review, commercial projects, peer impressions, Survey}, issn = {1939-3520}, doi = {10.1109/TSE.2016.2576451}, url = {https://amiangshu.com/papers/CodeReview-TSE-2016.pdf}, attachments = {https://flosshub.org/sites/flosshub.org/files/CodeReview-TSE-2016.pdf}, author = {Bosu, Amiangshu and Carver, Jeffrey C. and Christian Bird and Orbeck, Jonathan and Chockley, Christopher} } @proceedings {1899, title = {Progression and Forecast of a Curated Web-of-Trust: A Study on the Debian Project{\textquoteright}s Cryptographic Keyring}, volume = {496}, year = {2017}, month = {05/2017}, pages = {117-127}, publisher = {Springer}, abstract = {The Debian project is one of the largest free software undertakings worldwide. It is geographically distributed, and participation in the project is done on a voluntary basis, without a single formal employee or directly funded person. As we will explain, due to the nature of the project, its authentication needs are very strict{\textemdash}User/password schemes are way surpassed, and centralized trust management schemes such as PKI are not compatible with its distributed and flat organization; fully decentralized schemes such as the PGP Web of Trust are insuficient by themselves. The Debian project has solved this need by using what we termed a {\textquotedblleft}curated Web of Trust{\textquotedblright}. We will explain some lessons learned from a massive key migration process that was triggered in 2014. We will present the social insight we have found from examining the relationships expressed as signatures in this curated Web of Trust, some recommendations on personal key-signing policies, and a statistical study and forecast on aging, refreshment and survival of project participants stemming from an analysis on their key-handling.}, keywords = {cryptography, curated Web of Trust, debian, Keyring, trust management}, doi = {10.1007/978-3-319-57735-7_12}, url = {https://link.springer.com/chapter/10.1007/978-3-319-57735-7_12}, author = {Gunnar Wolf and V{\'\i}ctor Gonz{\'a}lez Quiroga} } @article {Krishnamurthy:2016:PDP:2869770.2820618, title = {Peripheral Developer Participation in Open Source Projects: An Empirical Analysis}, journal = {ACM Trans. Manage. Inf. Syst.}, volume = {6}, number = {4}, year = {2016}, pages = {14:1{\textendash}14:31}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {The success of the Open Source model of software development depends on the voluntary participation of external developers (the peripheral developers), a group that can have distinct motivations from that of project founders (the core developers). In this study, we examine peripheral developer participation by empirically examining approximately 2,600 open source projects. In particular, we hypothesize that peripheral developer participation is higher when the potential for building reputation by gaining recognition from project stakeholders is higher. We consider recognition by internal stakeholders (such as core developers) and external stakeholders (such as end-users and peers). We find a positive association between peripheral developer participation and the potential of stakeholder recognition after controlling for bug reports, feature requests, and other key factors. Our findings provide important insights for OSS founders and corporate managers for open sourcing or OSS adoption decisions. }, keywords = {Code ownership, open source software, project management, software metrics}, issn = {2158-656X}, doi = {10.1145/2820618}, url = {http://doi.acm.org/10.1145/2820618}, author = {Krishnamurthy, Rajiv and Jacob, Varghese and Radhakrishnan, Suresh and Kutsal Dogan} } @proceedings {1569, title = {PAID VS. VOLUNTEER WORK IN OPEN SOURCE}, year = {2014}, month = {01/2014}, pages = {3286-3295}, publisher = {IEEE Computer Society}, abstract = {Many open source projects have long become commercial. This paper shows just how much of open source software development is paid work and how much has remained volunteer work. Using a conservative approach, we find that about 50\% of all open source software development has been paid work for many years now and that many small projects are fully paid for by companies. However, we also find that any non-trivial project balances the amount of paid developer with volunteer work, and we suggest that the ratio of volunteer to paid work can serve as an indicator for the health of open source projects and aid the management of the respective communities.}, doi = {10.1109/HICSS.2014.407}, url = {http://dirkriehle.com/uploads/2013/08/paid-v8-final-web.pdf}, author = {Dirk Riehle and Riemer, Philipp and Carsten Kolassa and Michael Schmidt} } @inbook {1603, title = {A Performance Analysis of Wireless Mesh Networks Implementations Based on Open Source Software}, booktitle = {Open Source Software: Mobile Open Source Technologies}, series = {IFIP Advances in Information and Communication Technology}, volume = {427}, year = {2014}, pages = {107-110}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, abstract = { Wireless mesh networks (WMNs) have emerged as a promising technology, capable of provide broadband connectivity at low cost. Implementations based on Open Source Software of these networks offer advantages for providing broadband networking communications in scenarios where cabling is too expensive or prohibitive such as rural environments. In this paper we evaluate the performance of small scale wireless mesh WMN routing protocols for WMNs: B.A.T.M.A.N. Advanced and the 802.11s standard. We also compare an OpenFlow controller implemented over the WMN, verifying their bandwidth, datagram loss and jitter. }, keywords = {network performance, Open Source Software for research and innovation, OpenFlow, OpenWRT, Wireless Mesh Networks}, isbn = {978-3-642-55127-7}, doi = {10.1007/978-3-642-55128-4_14}, url = {http://dx.doi.org/10.1007/978-3-642-55128-4_14}, author = {Armuelles Voinov, Iv{\'a}n and Cede{\~n}o, AidelenChung and Chung, Joaqu{\'\i}n and Gonz{\'a}lez, Grace}, editor = {Corral, Luis and Sillitti, Alberto and Succi, Giancarlo and Vlasenko, Jelena and Wasserman, AnthonyI.} } @inbook {1616, title = {Polytrix: A Pacto-Powered Polyglot Test Matrix}, booktitle = {Open Source Software: Mobile Open Source Technologies}, series = {IFIP Advances in Information and Communication Technology}, volume = {427}, year = {2014}, pages = {191-194}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, abstract = { We have created a polyglot test framework named Polytrix to compare, benchmark, and independently verify a suite of open-source OpenStack SDKs that each target a different programming language. The framework validates sample code from each SDK against a shared test scenario to validate that each SDK correctly implements a given scenario. It uses Pacto for integration contract testing between the SDKs and the OpenStack services, and generates test reports that help compare and document each SDK. It is designed so interactive training materials can be generated in future versions. }, isbn = {978-3-642-55127-7}, doi = {10.1007/978-3-642-55128-4_27}, url = {http://dx.doi.org/10.1007/978-3-642-55128-4_27}, author = {Lincoln, Max and Alves, Fernando}, editor = {Corral, Luis and Sillitti, Alberto and Succi, Giancarlo and Vlasenko, Jelena and Wasserman, AnthonyI.} } @inbook {1623, title = {PROINFODATA: Monitoring a Large Park of Computational Laboratories}, booktitle = {Open Source Software: Mobile Open Source Technologies}, series = {IFIP Advances in Information and Communication Technology}, volume = {427}, year = {2014}, pages = {226-229}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, abstract = { This paper briefly presents a model for monitoring a large, heterogeneous and geographically scattered computer park. The data collection is performed by a software agent. The collected data are sent to the central server over the Internet, and stored by the storage system. An on-line portal makes up the visualization system, featuring charts, reports, and other tools for assessing the state of the park. This system is currently monitoring circa 150,000 machines. }, isbn = {978-3-642-55127-7}, doi = {10.1007/978-3-642-55128-4_34}, url = {http://dx.doi.org/10.1007/978-3-642-55128-4_34}, author = {Possamai, CleideL.B. and Pasqualin, Diego and Weingaertner, Daniel and Todt, Eduardo and Castilho, MarcosA. and Bona, LuisC.E. and Almeida, EduardoCunha}, editor = {Corral, Luis and Sillitti, Alberto and Succi, Giancarlo and Vlasenko, Jelena and Wasserman, AnthonyI.} } @conference {Kalliamvakou:2014:PPM:2597073.2597074, title = {The Promises and Perils of Mining GitHub}, booktitle = {Proceedings of the 11th Working Conference on Mining Software Repositories}, series = {MSR 2014}, year = {2014}, pages = {92{\textendash}101}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {With over 10 million git repositories, GitHub is becoming one of the most important source of software artifacts on the Internet. Researchers are starting to mine the information stored in GitHub{\textquoteright}s event logs, trying to understand how its users employ the site to collaborate on software. However, so far there have been no studies describing the quality and properties of the data available from GitHub. We document the results of an empirical study aimed at understanding the characteristics of the repositories in GitHub and how users take advantage of GitHub{\textquoteright}s main features---namely commits, pull requests, and issues. Our results indicate that, while GitHub is a rich source of data on software development, mining GitHub for research purposes should take various potential perils into consideration. We show, for example, that the majority of the projects are personal and inactive; that GitHub is also being used for free storage and as a Web hosting service; and that almost 40\% of all pull requests do not appear as merged, even though they were. We provide a set of recommendations for software engineering researchers on how to approach the data in GitHub. }, keywords = {bias, code reviews, git, github, mining software repositories}, isbn = {978-1-4503-2863-0}, doi = {10.1145/2597073.2597074}, url = {http://doi.acm.org/10.1145/2597073.2597074}, attachments = {https://flosshub.org/sites/flosshub.org/files/perils.pdf}, author = {Kalliamvakou, Eirini and Gousios, Georgios and Blincoe, Kelly and Singer, Leif and Daniel M. German and Damian, Daniela} } @book {1541, title = {A Preliminary Analysis of Localization in Free Software: How Translations Are Performed}, series = {IFIP Advances in Information and Communication TechnologyOpen Source Software: Quality Verification}, volume = {404}, year = {2013}, pages = {153 - 167}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, address = {Berlin, Heidelberg}, abstract = { Software is more than just source code. There is a myriad of elements that compose a software project, among others documentation, translations, multimedia, artwork, marketing. In this paper, we focus on the translation efforts that free, libre, open source software (FLOSS) projects undergo to provide their software in multiple languages. We have therefore analyzed a large amount of projects for their support and procedures regarding translations, if they exist. Our results show that many, but not all, projects offer some type of support and specify some ways to those wanting to contribute. Usually, projects from a more traditional libre software domain are more prone to ease such tasks. However, there is no general way to contribute, as formats and procedures are often project-specific. We have identified as well a high number of translation-supporting tools, with many projects having their own one. All in all, information about how to contribute is the main factor for having a very internationalized application. Projects accepting and giving credit to contributing translators have high levels of internationalization, even if the process is rudimentary. }, isbn = {978-3-642-38928-3}, issn = {1868-422X}, doi = {10.1007/978-3-642-38928-3_11}, author = {Reina, Laura Arjona and Gregorio Robles and Jesus M. Gonzalez-Barahona}, editor = {Petrinja, Etiel and Succi, Giancarlo and Ioini, Nabil and Sillitti, Alberto} } @article {IJC397, title = {Preliminary steps toward a general theory of internet-based collective-action in digital information commons: Findings from a study of open source software projects}, journal = {International Journal of the Commons}, volume = {7}, number = {2}, year = {2013}, abstract = {This paper presents some of the findings from a 5-year empirical study of FOSS (free/libre and open source software) commons, completed in 2011. FOSS projects are Internet-based common property regimes where the project source code is developed over the Internet. The resulting software is generally distributed with a license that provides users with the freedoms to access, use, read, modify and redistribute the software. In this study we used three different and very large datasets (approximately 107,000; 174,000 and 1400 cases respectively) with information on FOSS projects residing in Sourceforge.net, one of the largest, if not the largest, FOSS repository in the world. We employ various quantitative methods to uncover factors that lead some FOSS projects to ongoing collaborative success, while others become abandoned. After presenting some of our study{\textquoteright}s results, we articulate the collaborative {\textquotedblleft}story{\textquotedblright} of FOSS that emerged. We close the paper by discussing some key findings that can contribute to a general theory of Internet-based collective-action and FOSS-like forms of digital online commons.}, keywords = {collaborative success and abandonment, common property regime, digital information commons, flossmole, Free/libre software, open source software, sourceforge, srda}, issn = {1875-0281}, url = {http://www.thecommonsjournal.org/index.php/ijc/article/view/URN\%3ANBN\%3ANL\%3AUI\%3A10-1-114926}, author = {Charles Schweik and Robert English} } @conference {Scacchi:2013:PSO:2486046.2486068, title = {Processes in Securing Open Architecture Software Systems}, booktitle = {Proceedings of the 2013 International Conference on Software and System Process}, series = {ICSSP 2013}, year = {2013}, pages = {126{\textendash}135}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {Our goal is to identify and understand issues that arise in the development and evolution processes for securing open architecture (OA) software systems. OA software systems are those developed with a mix of closed source and open source software components that are configured via an explicit system architectural specification. Such a specification may serve as a reference model or product line model for a family of concurrently sustained OA system versions/variants. We employ a case study focusing on an OA software system whose security must be continually sustained throughout its ongoing development and evolution. We limit our focus to software processes surrounding the architectural design, continuous integration, release deployment, and evolution found in the OA system case study. We also focus on the role automated tools, software development support mechanisms, and development practices play in facilitating or constraining these processes through the case study. Our purpose is to identify issues that impinge on modeling (specification) and integration of these processes, and how automated tools mediate these processes, as emerging research problems areas for the software process research community. Finally, our study is informed by related research found in the prescriptive versus descriptive practice of these processes and tool usage in studies of conventional and open source software development projects.}, keywords = {configuration, continuous software development, Open architecture, process integration, process modeling, security}, isbn = {978-1-4503-2062-7}, doi = {10.1145/2486046.2486068}, url = {http://doi.acm.org/10.1145/2486046.2486068}, attachments = {https://flosshub.org/sites/flosshub.org/files/Scacchi-Alspaugh-ICSSP13.pdf}, author = {Walt Scacchi and Alspaugh, Thomas A.} } @proceedings {1489, title = {Project Roles in the Apache Software Foundation: A Dataset}, year = {2013}, month = {05/2013}, abstract = {This paper outlines the steps in the creation and maintenance of a new dataset listing leaders of the various projects of the Apache Software Foundation (ASF). Included in this dataset are different levels of committers to the various ASF project code bases, as well as regular and emeritus members of the ASF, and directors and officers of the ASF. The dataset has been donated to the FLOSSmole project under an open source license, and is available for download (https://code.google.com /p/flossmole/downloads/detail?name=apachePeople2013-Jan.zip), or for direct querying via a database client.}, keywords = {apache, dataset, roles}, attachments = {https://flosshub.org/sites/flosshub.org/files/apacheRolesPREPRINT.pdf , https://flosshub.org/sites/flosshub.org/files/MSR\%20presentation_0.pdf}, author = {Squire, Megan} } @proceedings {1459, title = {Perspectives on Code Forking and Sustainability in Open Source Software}, volume = {378}, year = {2012}, month = {09/2012}, pages = {274-279}, publisher = {IFIP AICT, Springer}, abstract = {The ability to create high-quality software artifacts that are usable over time is one of the essential requirements of the software business. In such a setting, open source software offers excellent opportunities for sustainability. In particular, safeguarding mechanisms against planned obsolescence by any single actor are built into the definition of open source. The most powerful of these mechanisms is the ability to fork the project. In this paper we argue that the possibility to fork serves as the invisible hand of sustainability that ensures that code remains open and that the code that best serves the community lives on. Furthermore, the mere option to fork provides a mechanism for safeguarding against despotic decisions by the project lead, who is thus guided in their actions to consider the best interest of the community.}, author = {Nyman, Linus and Mikkonen, Tommi and Juho Lindman and FougeĢ€re, Martin} } @proceedings {1290, title = {Package Upgrade Robustness: An Analysis for GNU/Linux Package Management Systems}, year = {2011}, month = {10/2011}, pages = {299-306}, publisher = {Springer}, abstract = {GNU/Linux systems are today used in servers, desktops, mobile and embedded devices. One of the critical operations is the installation and maintenance of software packages in the system. Currently there are no frameworks or tools for evaluating Package Management Systems (PMSs), such as RPM, in Linux and for measuring their reliability. The authors perform an analysis of the robustness of the RPM engine and discuss some of the current limitations. This article contributes to the enhancement of Software Reliability in Linux by providing a framework and testing tools under an open source license. These tools can easily be extended to other PMSs such as DEB packages or Gentoo Portage.}, keywords = {linux, package management, rpm}, author = {Thomson, John and Guerrriro, Andre and Paulo Trezentos and Johnson, Jeff} } @article {1420, title = {Path dependent stochastic models to detect planned and actual technology use: A case study of OpenOffice}, journal = {Information and Software Technology}, volume = {53}, year = {2011}, month = {11/2011}, pages = {1209 - 1226}, abstract = {Abstract Context Adopting IT innovation in organizations is a complex decision process driven by technical, social and economic issues. Thus, those organizations that decide to adopt innovation take a decision of uncertain success of implementation, as the actual use of a new technology might not be the one expected. The misalignment between planned and effective use of innovation is called assimilation gap. Objective This research aims at defining a quantitative instrument for measuring the assimilation gap and applying it to the case of the adoption of OSS. Method In this paper, we use the theory of path dependence and increasing returns of Arthur. In particular, we model the use of software applications (planned or actual) by stochastic processes defined by the daily amounts of files created with the applications. We quantify the assimilation gap by comparing the resulting models by measures of proximity. Results We apply and validate our method to a real case study of introduction of OpenOffice. We have found a gap between the planned and the effective use despite well-defined directives to use the new OS technology. These findings suggest a need of strategy re-calibration that takes into account environmental factors and individual attitudes. Conclusions The theory of path dependence is a valid instrument to model the assimilation gap provided information on strategy toward innovation and quantitative data on actual use are available.}, keywords = {Actual use of technology, Path dependence, Technology adoption, Urn models}, issn = {09505849}, doi = {10.1016/j.infsof.2011.05.002}, url = {http://www.sciencedirect.com/science/article/pii/S0950584911001042}, author = {Rossi, Bruno and Russo, Barbara and Succi, Giancarlo} } @proceedings {1275, title = {Preparing FLOSS for Future Network Paradigms: A Survey on Linux Network Management}, year = {2011}, month = {10/2011}, pages = {75-89}, publisher = {Springer}, abstract = {Operating system tools must fulfill the requirements generated by the advances in networking paradigms. To understand the current state of the Free, Libre and Open Source Software (FLOSS) ecosystem, we present a survey on the main tools used to manage and interact with the network, and how they are organized in Linux-based operating systems. Based on the survey results, we present a reference Linux network stack that can serve as the basis for future heterogeneous network environments, contributing towards a standardized approach in Linux. Using this stack, and focusing on dynamic and spontaneous network interactions, we present an evolution path for network related technologies, contributing to Linux as a network research operating system and to FLOSS as a whole.}, keywords = {linux, networking, Survey}, author = {Matos, Alfredo and Thomson, John and Paulo Trezentos} } @conference {1406, title = {Process Mining Software Repositories}, booktitle = {15th European Conference on Software Maintenance and Reengineering (CSMR 2011) }, year = {2011}, pages = {5 - 14}, publisher = {IEEE}, organization = {IEEE}, address = {Oldenburg, Germany}, abstract = {Software developers{\textquoteright} activities are in general recorded in software repositories such as version control systems, bug trackers and mail archives. While abundant information is usually present in such repositories, successful information extraction is often challenged by the necessity to simultaneously analyze different repositories and to combine the information obtained. We propose to apply process mining techniques, originally developed for business process analysis, to address this challenge. However, in order for process mining to become applicable, different software repositories should be combined, and {\textquotedblleft}related{\textquotedblright} software development events should be matched: e.g., mails sent about a file, modifications of the file and bug reports that can be traced back to it. The combination and matching of events has been implemented in FRASR (FRamework for Analyzing Software Repositories), augmenting the process mining framework ProM. FRASR has been successfully applied in a series of case studies addressing such aspects of the development process as roles of different developers and the way bug reports are handled.}, keywords = {amsn, email, email archives, gcc, mailing list, Process mining, software repositories}, isbn = {978-1-61284-259-2}, doi = {10.1109/CSMR.2011.5}, attachments = {https://flosshub.org/sites/flosshub.org/files/2011-03_CSMR.pdf}, author = {Poncin, Wouter and Serebrenik, Alexander and Brand, Mark van den} } @conference {835, title = {Paying attention to each other in visible work communities: Modeling bursty systems of multiple activity streams}, booktitle = {SocialCom/PASSAT(2010)}, year = {2010}, note = {Uses open source projects to study, but this is not about open source, per se.}, month = {2010}, pages = {276-281}, abstract = {Online work projects, from open source to wikipedia, have emerged as an important phenomenon. These communities offer exciting opportunities to investigate social processes because they leave traces of their activity over time. Unlike traditional work teams, the participants in these communities are widely dispersed and work without centralized management. The question arises, then, as to the extent to which these are in fact communities: is the group simply the sum of the individuals that make it up, or does the group function as a social unit? We explore this question in the temporal domain. We argue that the rapid visibility of others{\textquoteright} work afforded by the information systems used by these projects reaches out and attracts the attention of others who are peripherally aware of the group{\textquoteright}s online space, prompting them to begin or intensify their participation, binding separate individual streams of activity into a social entity. Previous work has suggested that for certain types of bursty social behavior (e.g. email), the frequency of the behavior is not homogeneously distributed but rather can be divided into two generative mechanisms: active sessions and passive background participation. We extend this work for the case of multiple conditionally independent streams of behavior, where each stream is generated by these two generative mechanisms. Our model can characterized by a double-chain hidden Markov model, allowing efficient inference using expectation-maximization. We apply this model to visible work communities by modeling each participant as a single stream of behavior, assessing transition probabilities between active sessions of different participants. This allows us to examine the extent to which the various members of the community are influenced by the active participation of others. Our results indicate that an active session by a participant at least triples the likelihood of another participant beginning an active session.}, attachments = {https://flosshub.org/sites/flosshub.org/files/olson2010paying-attentio.pdf}, author = {Olson, Jamie F and Howison, James and Carley, Kathleen} } @conference {955, title = {Perspectives on bugs in the Debian bug tracking system}, booktitle = {2010 7th IEEE Working Conference on Mining Software Repositories (MSR 2010)2010 7th IEEE Working Conference on Mining Software Repositories (MSR 2010)}, year = {2010}, pages = {86 - 89}, publisher = {IEEE}, organization = {IEEE}, address = {Cape Town, South Africa}, abstract = {Bugs in Debian differ from regular software bugs. They are usually associated with packages, instead of software modules. They are caused and fixed by source package uploads instead of code commits. The majority are reported by individuals who appear in the bug database once, and only once. There also exists a small group of bug reporters with over 1,000 bug reports each to their name. We also explore our idea that a high bug-frequency for an individual package might be an indicator of popularity instead of poor quality.}, keywords = {bug reports, debian, msr challenge, popularity}, isbn = {978-1-4244-6802-7}, doi = {10.1109/MSR.2010.5463288}, attachments = {https://flosshub.org/sites/flosshub.org/files/86bugs-debian.pdf}, author = {Davies, Julius and Hanyu Zhang and Nussbaum, Lucas and Daniel M. German} } @conference {949, title = {Predicting the severity of a reported bug}, booktitle = {2010 7th IEEE Working Conference on Mining Software Repositories (MSR 2010)2010 7th IEEE Working Conference on Mining Software Repositories (MSR 2010)}, year = {2010}, pages = {1 - 10}, publisher = {IEEE}, organization = {IEEE}, address = {Cape Town, South Africa}, abstract = {The severity of a reported bug is a critical factor in deciding how soon it needs to be fixed. Unfortunately, while clear guidelines exist on how to assign the severity of a bug, it remains an inherent manual process left to the person reporting the bug. In this paper we investigate whether we can accurately predict the severity of a reported bug by analyzing its textual description using text mining algorithms. Based on three cases drawn from the open-source community (Mozilla, Eclipse and GNOME), we conclude that given a training set of sufficient size (approximately 500 reports per severity), it is possible to predict the severity with a reasonable accuracy (both precision and recall vary between 0.65-0.75 with Mozilla and Eclipse; 0.70-0.85 in the case of GNOME).}, keywords = {bug reports, eclipse, gnome, mozilla, severity, text mining}, isbn = {978-1-4244-6802-7}, doi = {10.1109/MSR.2010.5463284}, attachments = {https://flosshub.org/sites/flosshub.org/files/1lamkanfiDemeyer1.pdf}, author = {Lamkanfi, Ahmed and Demeyer, Serge and Giger, Emanuel and Goethals, Bart} } @article {1558, title = {Proposed Application of Data Mining Techniques for Clustering Software Projects}, journal = {INFOCOMP Special Edition}, year = {2010}, note = {"Using data available on the web, mainly in software repositories, a collaborative project called FLOSSmole was created to collect, share, and store comparable data and analysis of the FLOSS development for academic research. The project is based on continuous data collection and analysis efforts of many research groups, reducing duplication and promoting compatibility both in the data sources of FLOSS software, as well as in research and analysis [6]. In the FLOSSmole project, data was collected in different software repositories. This data was stored in relational databases (SQL), and available on FLOSSmole Project website [2]. For this study, we used the database collected from SourceForge repository, as they are the largest repository of projects today, and it is well known among developers." }, pages = {43-48}, abstract = {Software projects always generate a lot of data, ranging from informal documentation to a database with thousands of lines of code. This information extracted from software projects takes even greater when it comes to OSS (Open Source Software). Such data may include source code base, historical change in the software, bug reports, mailing lists, among others. Using data mining techniques, we can extract valuable knowledge of this set of in formation, thus providing improvements throughout the process of software development. The results can be used to improve the quality of software, or even to manage the project in order to obtain maximum efficiency. This article proposes the application of data mining techniques to cluster software projects, cites the advantages that can be obtained with these techniques, and illustrates the application of data mining in a Open Source Software database}, keywords = {flossmole}, attachments = {https://flosshub.org/sites/flosshub.org/files/art06.pdf}, author = {Rezende, Henrique Ribiero and Esmin, Ahmed Ali Abdalla} } @conference {611, title = {Panel: Governance in Open Source Projects and Communities}, booktitle = {OSS2009: Open Source Ecosystems: Diverse Communities Interacting (IFIP 2.13)}, series = {IFIP Advances in Information and Communication Technology }, volume = {299/2009}, year = {2009}, month = {2009///}, pages = {370 - 370}, publisher = {Springer}, organization = {Springer}, chapter = {43}, abstract = {{\textquotedblleft}Although considerable research has been devoted to the growth and expansion of open source communities and the comparison between the efficiency of corporate structures and community structures in the field of software development, rather less attention has been paid to their governance structures (control, monitoring, supervision){\textquotedblright} (Lattemann and Stieglitz 2005). }, issn = {978-3-642-02031-5}, doi = {http://dx.doi.org/10.1007/978-3-642-02032-2_43}, attachments = {https://flosshub.org/sites/flosshub.org/files/Panel\%20Governnance.pdf}, author = {Bolici, Francesco and de Laat, Paul and Ljungberg, Jan and Pontiggia, Andrea and Rossi Lamastra, Cristina} } @conference {610, title = {Panel: Open Source in the Public Sector}, booktitle = {OSS2009: Open Source Ecosystems: Diverse Communities Interacting (IFIP 2.13)}, series = {IFIP Advances in Information and Communication Technology }, volume = {299/2009}, year = {2009}, month = {2009///}, pages = {368 - 369}, publisher = {Springer}, organization = {Springer}, chapter = {42}, abstract = {Open Source Software (OSS) is becoming mainstream, and it is perhaps not surprising that public sector organisations seek to explore the potential of OSS in financially difficult times. Today, OSS has become an issue of strategic importance for many public sector organisations. In addition, related to OSS, many organisations and governments are also acknowledging Open Standards as important for addressing various lock-in scenarios. }, issn = {978-3-642-02031-5}, doi = {http://dx.doi.org/10.1007/978-3-642-02032-2_42}, attachments = {https://flosshub.org/sites/flosshub.org/files/Panel\%20Open\%20Source.pdf}, author = {Lundell, Bj{\"o}rn and Amundsen, Morten and Ghosh, Rishab and Hardy, Jean-Luc and Sj{\"o}sw{\"a}rd, Per-Ola} } @article {Barcellini2009533, title = {Participation in online interaction spaces: Design-use mediation in an Open Source Software community}, journal = {International Journal of Industrial Ergonomics}, volume = {39}, number = {3}, year = {2009}, note = {Selected papers from ECCE 2007, the 25th Anniversary Conference of the European Conference on Cognitive Ergonomics}, pages = {533 - 540}, abstract = {This research aims at characterizing emerging roles fostering design-use mediation during the Open Source Software (OSS) design process through the analysis of participation. Studying OSS is of particular interest: (1) to investigate socio-technical settings supporting user participation to the design process, which is considered to be the major strength of OSS design; (2) to gain insights into supporting the changing nature of the software industry, which is becoming more and more distributed and global, and which is thus increasingly making use of OSS design tools and methods. In this research, we characterized effective roles of participants, i.e. participation, on the basis of activities analysis in three online interaction spaces (discussion, documentation and implementation) during a continuous {\textquotedblleft}pushed-by-users{\textquotedblright} design process of the Python project. Participation is targeted through a methodology articulating: (1) structural analyses (organization of the discussions, regularity and involvement of participants, quotes-based social network) in usage-oriented and development-oriented mailing lists of the projects{\textquoteright} discussion space; (2) actions to the code and documentation made by participants in the implementation and documentation spaces. Besides the importance of the users{\textquoteright} contribution to the process, OSS design is fostered by some key-participants, the cross-participants, who act as boundary spanners between the developers and the users, helping them to go beyond some barriers to participation. These findings can be reinforced developing software to automate the structural analysis of discussions and actions to the code and documentation.}, keywords = {Distributed participatory design}, issn = {0169-8141}, doi = {10.1016/j.ergon.2008.10.013}, url = {http://www.sciencedirect.com/science/article/pii/S0169814108001637}, author = {Barcellini, Flore and D{\'e}tienne, Fran{\c c}oise and Burkhardt, Jean-Marie} } @conference {593, title = {Peeling the Onion}, booktitle = {OSS2009: Open Source Ecosystems: Diverse Communities Interacting (IFIP 2.13)}, series = {IFIP Advances in Information and Communication Technology }, volume = {299/2009}, year = {2009}, month = {2009///}, pages = {284 - 297}, publisher = {Springer}, organization = {Springer}, chapter = {25}, abstract = {According to the now widely accepted {\textquotedblleft}onion-model{\textquotedblright} of the organization of open source software development, an open source project typically relies on a core of developers that is assisted by a larger periphery of users. But what does the role of the periphery consist of? Raymond{\textquoteright}s Linus{\textquoteright}s Law which states that {\textquotedblleft}given enough eyeballs all bugs are shallow{\textquotedblright} suggests at least one important function: the detection of defects. Yet, what are the ways through which core and periphery interact with each other? With the help of text-mining methods, we study the treatment of bugs that affected the Firefox Internet browser as reflected in the discussions and actions recorded in Mozilla{\textquoteright}s issue tracking system Bugzilla. We find various patterns in the modes of interactions between core and peripheral members of the community. For instance, core members seem to engage more frequently with the periphery when the latter proposes a solution (a patch). This leads us to conclude that Alan Cox{\textquoteright}s dictum {\textquotedblleft}show me the code{\textquotedblright}, perhaps even more than Linus{\textquoteright}s law, seems to be the dominant rule that governs the development of software like Firefox. }, issn = {978-3-642-02031-5}, doi = {http://dx.doi.org/10.1007/978-3-642-02032-2_25}, attachments = {https://flosshub.org/sites/flosshub.org/files/Peeling\%20the\%20Onion.pdf}, author = {Masmoudi, H{\'e}la and den Besten, Matthijs and de Loupy, Claude and Jean-Michel Dalle} } @booklet {859, title = {Perceptions and Practices of Usability in the Free/Open Source Software (FOSS) Community}, number = {CS-2009-26}, year = {2009}, publisher = {David R. Cheriton School of Computer Science, University of Waterloo}, author = {Terry, M. and Kay, M. and Lafreniere, B.} } @conference {924, title = {A platform for software engineering research}, booktitle = {2009 6th IEEE International Working Conference on Mining Software Repositories (MSR)2009 6th IEEE International Working Conference on Mining Software Repositories}, year = {2009}, pages = {31 - 40}, publisher = {IEEE}, organization = {IEEE}, address = {Vancouver, BC, Canada}, abstract = {Research in the fields of software quality, maintainability and evolution requires the analysis of large quantities of data, which often originate from open source software projects. Collecting and preprocessing data, calculating metrics, and synthesizing composite results from a large corpus of project artifacts is a tedious and error prone task lacking direct scientific value. The Alitheia Core tool is an extensible platform for software quality analysis that is designed specifically to facilitate software engineering research on large and diverse data sources, by integrating data collection and preprocessing phases with an array of analysis services, and presenting the researcher with an easy to use extension mechanism. Alitheia Core aims to be the basis of an ecosystem of shared tools and research data that will enable researchers to focus on their research questions at hand, rather than spend time on re-implementing analysis tools. In this paper, we present the Alitheia Core platform in detail and demonstrate its usefulness in mining software repositories by guiding the reader through the steps required to execute a simple experiment.}, keywords = {alitheia core}, isbn = {978-1-4244-3493-0}, doi = {10.1109/MSR.2009.5069478}, attachments = {https://flosshub.org/sites/flosshub.org/files/31gousios.pdf}, author = {Gousios, Georgios and Diomidis Spinellis} } @conference {DBLP:conf/msr/BirdRBHGD09, title = {The promises and perils of mining git}, booktitle = {Proceedings of the 6th International Working Conference on Mining Software Repositories, MSR 2009}, year = {2009}, pages = {1-10}, abstract = {We are now witnessing the rapid growth of decentralized source code management (DSCM) systems, in which every developer has her own repository. DSCMs facilitate a style of collaboration in which work output can flow sideways (and privately) between collaborators, rather than always up and down (and publicly) via a central repository. Decentralization comes with both the promise of new data and the peril of its misinterpretation. We focus on git, a very popular DSCM used in high-profile projects. Decentralization, and other features of git, such as automatically recorded contributor attribution, lead to richer content histories, giving rise to new questions such as "How do contributions flow between developers to the official project repository?" However, there are pitfalls. Commits may be reordered, deleted, or edited as they move between repositories. The semantics of terms common to SCMs and DSCMs sometimes differ markedly, potentially creating confusion. For example, a commit is immediately visible to all developers in centralized SCMs, but not in DSCMs. Our goal is to help researchers interested in DSCMs avoid these and other perils when mining and analyzing git data.}, keywords = {dscm, git, mining, scm, source code}, attachments = {https://flosshub.org/sites/flosshub.org/files/1promisePeril.pdf}, author = {Christian Bird and Peter C. Rigby and Earl T. Barr and David J. Hamilton and Daniel M. Germ{\'a}n and Premkumar T. Devanbu} } @conference {576, title = {Providing Commercial Open Source Software: Lessons Learned}, booktitle = {OSS2009: Open Source Ecosystems: Diverse Communities Interacting (IFIP 2.13)}, series = {IFIP Advances in Information and Communication Technology }, volume = {299/2009}, year = {2009}, month = {2009///}, pages = {70 - 82}, publisher = {Springer}, organization = {Springer}, chapter = {8}, abstract = {Even though companies like Sun, IBM, MySQL and others have released several commercial Open Source Software (OSS) products, little evidence exist of how to successfully launch such products and establish a living community around them. This paper presents a case study from a small software company succeeding at establishing a business model and a vivid community around their own OSS products. Based on this case study, the paper presents lessons learned which could help other OSS providers. }, issn = {978-3-642-02031-5}, doi = {http://dx.doi.org/10.1007/978-3-642-02032-2_8}, attachments = {https://flosshub.org/sites/flosshub.org/files/Providing\%20Commercial\%20Open\%20Source.pdf}, author = {Hauge, {\O}yvind and Ziemer, Sven} } @conference {bird2009pat, title = {{Putting it All Together: Using Socio-Technical Networks to Predict Failures}}, booktitle = {Proceedings of the 17th International Symposium on Software Reliability Engineering}, year = {2009}, note = {First, we build each type of network separately and use network analysis on both to gather metrics for use in a predictive model. Second, we build a socio-technical network which combines the nodes and edges from both the dependency network and the contribution network and use metrics gathered from this network in a predictive model. We evaluate our approach by collecting data from Mi- crosoft Windows Vista and ECLIPSE development and using logistic regression analysis.}, abstract = {Studies have shown that social factors in development organizations have a dramatic effect on software quality. Separately, program dependency information has also been used successfully to predict which software components are more fault prone. Interestingly, the influence of these two phenomena have only been studied separately. Intuition and practical experience suggests, however, that task assignment (i.e. who worked on which components and how much) and dependency structure (which components have dependencies on others) together interact to influence the quality of the resulting software. We study the influence of combined socio-technical software networks on the fault-proneness of individual software components within a system. The network properties of a software component in this combined network are able to predict if an entity is failure prone with greater accuracy than prior methods which use dependency or contribution information in isolation. We evaluate our approach in different settings by using it on Windows Vista and across six releases of the Eclipse development environment including using models built from one release to predict failure prone components in the next release. We compare this to previous work. In every case, our method performs as well or better and is able to more accurately identify those software components that have more post-release failures, with precision and recall rates as high as 85\%.}, keywords = {eclipse, microsoft, social network, vista, windows}, attachments = {https://flosshub.org/sites/flosshub.org/files/bird2009pat.pdf}, author = {Christian Bird and Nachiappan Nagappan and Devanbu, Premkumar and Gall, Harald and Brendan Murphy} } @conference {567, title = {Panel: Opportunities and Risks for Open Source Software in Industry}, booktitle = {OSS2008: Open Source Development, Communities and Quality (IFIP 2.13)}, series = {IFIP International Federation for Information Processing}, volume = {275/2008}, year = {2008}, month = {2008///}, pages = {413 - 414}, publisher = {Springer}, organization = {Springer}, chapter = {40}, abstract = {Open Source Software (OSS) is a multi-faceted phenomenon which has become an issue of strategic importance for many commercial organisations. Stemming from an ideological issue, with emphasis on freedom and community values, we have recently seen a broader interest in the Open Source phenomenon amongst practitioners in many companies. A number of SMEs and large companies are currently exploring the potential of Open Source, and for some it has become core to their business and development activities. }, issn = {978-0-387-09683-4}, doi = {http://dx.doi.org/10.1007/978-0-387-09684-1_40}, attachments = {https://flosshub.org/sites/flosshub.org/files/Panel\%20Opportunities\%20\%26\%20Risks.pdf}, author = {Feller, Joseph and Lundell, Bj{\"o}rn and Marttiin, Pentti and Walt Scacchi and Schellingerhout, Nico} } @article {501, title = {PhD Candidate Paper}, journal = {Science Studies}, number = {2}, year = {2008}, month = {Feb}, abstract = {National legislation to mandate the use or consideration of Free/Libre and Open Source Software (FLOSS) in government institutions is increasingly emerging as a strategy for FLOSS advocates in Latin America and the broader developing world. Such movements for the political use and regulation of FLOSS mark a distinct turn in the objectives and work of FLOSS advocates, whose activities largely focused on the dissemination of FLOSS as a technological artifact. This paper investigates the network of diverse actors involved in promoting FLOSS legislation in Peru, one of the first nations where a movement for FLOSS legislation emerged. It emphasizes that crucial to the work of FLOSS{\textquoteright} network actors is not their merely technological productivity, but their cultural and political productivity - that is, their ability to produce diverse body of meaning made both evident and mobile in narratives of FLOSS use and adoption.}, attachments = {https://flosshub.org/sites/flosshub.org/files/Chan_ScienceStudies.pdf}, author = {Anita Say Chan} } @conference {532, title = {PMLite: An Open Source Solution for Process Monitoring}, booktitle = {OSS2008: Open Source Development, Communities and Quality (IFIP 2.13)}, series = {IFIP International Federation for Information Processing}, volume = {275/2008}, year = {2008}, month = {2008///}, pages = {57 - 68}, publisher = {Springer}, organization = {Springer}, chapter = {5}, abstract = {Process Monitoring represents a big challenge for organizations that aim to manage software projects adopting different development paradigms. In fact, across-process enterprise-level measurement campaigns can be difficult to enact since process attributes to retrieve are semantically diverse and may be difficult to integrate. In this paper, we present PMLite (Process Monitoring Lite) an open source solution to this problem. PMLite is based on an open metamodel and paves the way to the definition of ad-hoc open monitoring frameworks. }, issn = {978-0-387-09683-4}, doi = {http://dx.doi.org/10.1007/978-0-387-09684-1_5}, attachments = {https://flosshub.org/sites/flosshub.org/files/PMLite.pdf}, author = {Colombo, Alberto and Damiani, Ernesto and Frati, Fulvio} } @conference {Krogstie:2008:PTB:1368088.1368201, title = {Power through brokering: open source community participation in software engineering student projects}, booktitle = {Proceedings of the 30th international conference on Software engineering}, series = {ICSE {\textquoteright}08}, year = {2008}, pages = {791{\textendash}800}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {Many software engineering projects use open source software tools or components. The project team{\textquoteright}s active participation in the open source community may be necessary for the team to use the technology. Based on an in-depth field study of industry software engineering project students interacting with an open source community, we find that participation in the community may affect the team{\textquoteright}s work and learning by strengthening the power of the broker between the team and the community. We outline pitfalls and benefits of having student teams acquire development-related knowledge from open source communities. The findings are relevant to the organization and supervision of software engineering student projects interacting with open source communities.}, keywords = {Communities Of Practice, computer science education, FLOSS, open source, software engineering, software engineering education}, isbn = {978-1-60558-079-1}, doi = {10.1145/1368088.1368201}, url = {http://doi.acm.org/10.1145/1368088.1368201}, author = {Krogstie, Birgit R.} } @booklet {520, title = {Preparing the Ne(x)t Generation: Lessons learnt from Free/Libre Open Source Software and their Communities}, year = {2008}, month = {Sept}, abstract = {In this article, the authors Andreas Meiszner, R{\~A}{\textonequarter}diger Glott and Sulayaman K. Sowe, examine the lessons that can be learnt from the Free / Libre Open and Source Software (FLOSS) communities. FLOSS communities, as good practice examples of Open Participatory Learning Ecosystems, illustrate possible pathways for higher education to go beyond the limits of the current Open Educational Resource move.}, attachments = {https://flosshub.org/sites/flosshub.org/files/GUNI_paper_proceedings_Meiszner_Glott_Sowe.pdf}, author = {Andreas Meiszner and R{\"u}dige Glott and Sowe, Sulayman K.} } @unpublished {flosswp387, title = {Promoting the Penguin: Who is Advocating Open Source Software in Commercial Settings?}, year = {2008}, month = {March}, abstract = {Most firms that use or develop software today face the questions of whether and how to engage in open source software (OSS). Yet, little is known about the process of OSS adoption and diffusion within corporations. Guided by the models of Rogers (innovation diffusion) and Davis (Technology Acceptance Model), we develop a theoretical framework of how job function influences individuals? proclivity to support their employers? adoption of OSS and OSS practices. We argue that job function determines an individual?s tasks, and that different tasks are differentially affected by OSS. Our study is based on interviews and a large-scale survey in a multinational corporation. Distinguishing between developers, testers, software architects, project managers, and managers, we find greater engagement in OSS to be favored most strongly by testers. Excepting project managers, developers, despite having the most experience with OSS, are the least favorably disposed to greater corporate OSS engagement. A corporation interested in adopting OSS should thus take into account the job function-related incentives of each individual. More generally, we propose that models predicting IT adoption behavior be extended to account for the ways in which individual adopters interact with the innovation at hand, which will be determined largely by their job functions.}, author = {Oliver Alexy and Joachim Henkel} } @inbook {812, title = {Patchworks of Open-Source Software: High-Fidelity Low-cost Prototypes. }, booktitle = {The Handbook of Research on Open Source Software. }, year = {2007}, pages = {126-140.}, publisher = {Idea Group, Inc.}, organization = {Idea Group, Inc.}, author = {Jones, M.C. and Floyd, I.R. and Twidale, M.B} } @article {flosswp375, title = {Penguin in a new suit: A tale of how de novo entrants emerged to harness free and open source communities}, year = {2007}, month = {October}, abstract = {A growing body of literature has explored the motivations for individuals to take part in free and open source software (FOSS), yet how firms participate is largely an unattended research area. Building on information from an extensive dataset of secondary sources and 30 in-depth interviews, I show that de novo entrants have emerged in conjunction with a changing institutional infrastructure and a more pragmatic attitude toward firms that focus on technological benefits rather than ideology. To understand how these firms try to harness the work of these communities, I use the empirical data to derive a 2*2 matrix of different approaches. The X axis reflects whether or not the firms initiated a new community or relied on communities founded by peers, whereas the Y axis represents the degree of participation of the firm in the community. This taxonomy illustrates how de novo entrant are initiating new forms of communities or joining communities established by peers. This suggests that while many of the central pillars of FOSS remains, de novo entrants have emerged to find new ways of making business resulting in various implications for firm strategies and knowledge disclosure. PLEASE EMAIL IF YOU LIKE A COPY OF THE PAPER!}, attachments = {https://flosshub.org/sites/flosshub.org/files/dahlander2007.pdf}, author = {Linus Dahlander} } @conference {651, title = {Perceptions on F/OSS Adoption}, booktitle = {OSS2007: Open Source Development, Adoption and Innovation (IFIP 2.13)}, series = {IFIP International Federation for Information Processing }, volume = {234/2007}, year = {2007}, month = {2007///}, pages = {319 - 324}, publisher = {Springer}, organization = {Springer}, chapter = {35}, abstract = {This paper aims to reveal results of a survey run by the tOSSad1 project. The majority of survey variables devised to capture perception of public administrators around Europe regarding the importance they attach to the factors such as F/OSS product quality, availability of support, expertise and documentation, TCO, vendor lock-in, political influence, administrative attitudes, productivity, and training costs, all of which intermingle with financial, technical, legal, and personal issues. The analysis consist of depiction of respondents{\textquoteright} administration profile in terms of their F/OSS usage and adoption, descriptive summary and analyses of factors mentioned above, and statistical inferential analyses of survey items. Some valid statistical tests are conducted to understand, to discuss and to see the extend and significance of any F/OSS adoption generalizations for Europe based on the findings of this particular survey. }, issn = {978-0-387-72485-0}, doi = {http://dx.doi.org/10.1007/978-0-387-72486-7_35}, attachments = {https://flosshub.org/sites/flosshub.org/files/Perceptions\%20on\%20F\%20OSS.pdf}, author = {Ozel, Bulent and Jovanovic, Uros and Oba, Beyza and van Leeuwen, Manon} } @conference {1016, title = {Predicting Defects and Changes with Import Relations}, booktitle = {Fourth International Workshop on Mining Software Repositories (MSR{\textquoteright}07:ICSE Workshops 2007)}, year = {2007}, pages = {31 - 31}, publisher = {IEEE}, organization = {IEEE}, address = {Minneapolis, MN, USA}, abstract = {Lowering the number of defects and estimating the development time of a software project are two important goals of software engineering. To predict the number of defects and changes we train models with import relations. This enables us to decrease the number of defects by more efficient testing and to assess the effort needed in respect to the number of changes.}, keywords = {defects, eclipse, effort estimation, mining challenge, msr challenge, prediction}, isbn = {0-7695-2950-X}, doi = {10.1109/MSR.2007.24}, attachments = {https://flosshub.org/sites/flosshub.org/files/28300031.pdf}, author = {Schroter, Adrian} } @conference {1014, title = {Predicting Eclipse Bug Lifetimes}, booktitle = {Fourth International Workshop on Mining Software RepositoriesFourth International Workshop on Mining Software Repositories (MSR{\textquoteright}07:ICSE Workshops 2007)}, year = {2007}, pages = {29 - 29}, publisher = {IEEE}, organization = {IEEE}, address = {Minneapolis, MN, USA}, abstract = {In non-trivial software development projects planning and allocation of resources is an important and difficult task. Estimation of work time to fix a bug is commonly used to support this process. This research explores the viability of using data mining tools to predict the time to fix a bug given only the basic information known at the beginning of a bug{\textquoteright}s lifetime. To address this question, a historical portion of the Eclipse Bugzilla database is used for modeling and predicting bug lifetimes. A bug history transformation process is described and several data mining models are built and tested. Interesting behaviours derived from the models are documented. The models can correctly predict up to 34.9\% of the bugs into a discretized log scaled lifetime class.}, keywords = {bug fixing, bugzilla, classification, eclipse, effort estimation, mining challenge, msr challenge, prediction, weka}, isbn = {0-7695-2950-X}, doi = {10.1109/MSR.2007.25}, attachments = {https://flosshub.org/sites/flosshub.org/files/28300029.pdf}, author = {Panjer, Lucas D.} } @conference {1214, title = {A Preliminary Analysis of Publicly Available FLOSS Measurements: Towards Discovering Maintainability Trends}, booktitle = {2nd Workshop on Public Data about Software Development (WoPDaSD 2007)}, year = {2007}, note = {used SourceKibitzer data downloaded from FLOSSmole}, month = {2007}, abstract = {The spread of free/libre/open source software (FLOSS) and the openness of its development model offer researchers a valuable source of information regarding software data. The creation of large portals, which host a vast amount of FLOSS projects make it easy to create large datasets with valuable information regarding the FLOSS development process. In addition initiatives such as FLOSSMole provide researchers with a single point and continuing access to those data. Up to now the majority of datasets from FLOSSMole offered data regarding the development process and not the code itself. From February 2007 FLOSSMole offers data donated by SourceKibitzer, which contain source code metrics for FLOSS projects written in Java. In this paper we provide a premilinary analysis on those data using machine learning techniques, such as classification rules and decision trees. Using the first available data from February 2007, we tried to build rules that can be used in order to estimate the future values of metrics offered for March. Here we present some preliminary results that are encouraging and deserve to be further analyzed in future releases of SourceKibitzer datasets. }, keywords = {decision tree, flossmole, java, machine learning, metrics, sourcekibitzer}, attachments = {https://flosshub.org/sites/flosshub.org/files/Samolades2007.pdf}, author = {Samoladas, Ioannis and Bibi, Stamatia and Ioannis Stamelos and Sowe, Sulayman K. and Deligiannis, Ignatios} } @conference {1012, title = {Prioritizing Warning Categories by Analyzing Software History}, booktitle = {Fourth International Workshop on Mining Software Repositories (MSR{\textquoteright}07:ICSE Workshops 2007)}, year = {2007}, pages = {27 - 27}, publisher = {IEEE}, organization = {IEEE}, address = {Minneapolis, MN, USA}, abstract = {Automatic bug finding tools tend to have high false positive rates: most warnings do not indicate real bugs. Usually bug finding tools prioritize each warning category. For example, the priority of "overflow" is 1 and the priority of "jumbled incremental" is 3, but the tools{\textquoteright} prioritization is not very effective. In this paper, we prioritize warning categories by analyzing the software change history. The underlying intuition is that if warnings from a category are resolved quickly by developers, the warnings in the category are important. Experiments with three bug finding tools (FindBugs, JLint, and PMD) and two open source projects (Columba and jEdit) indicate that different warning categories have very different lifetimes. Based on that observation, we propose a preliminary algorithm for warning category prioritizing.}, keywords = {bug fixing, change history, columba, findbugs, jedit, jlint, kenyon, pmd, warning}, isbn = {0-7695-2950-X}, doi = {10.1109/MSR.2007.26}, attachments = {https://flosshub.org/sites/flosshub.org/files/28300027.pdf}, author = {Kim, Sunghun and Ernst, Michael D.} } @proceedings {66, title = {Productivity effects of information diffusion in email networks}, year = {2007}, address = {Montr{\'e}al, PQ, Canada}, author = {Sinan Aral and Erik Brynjolfsson and Marshall Van Alstyne} } @conference {1225, title = {Programming Language Trends in Open Source Development: An Evaluation Using Data from All Production Phase SourceForge Projects}, booktitle = {2nd Workshop on Public Data about Software Development (WoPDaSD 2007)}, year = {2007}, note = {"Our data were gathered from the SourceForge Research Ar- chive (SFRA) [4] and the CVS repositories Open Source projects hosted on SourceForge. We used cvs2mysql and SFRA+ to collect the data. cvs2mysql gathers data from CVS repositories and writes them to SQL scripts for im- port into a MySQL 5.0 database. The data collected by cvs2mysql are the name of the file, the location of the file in the repository, the type and state of the file, as well as the author, date, number of lines added and removed, and the author{\textquoteright}s message for each revision to the file."}, abstract = {In this work, we analyze data collected from the CVS repos- itories of 9,997 Open Source projects hosted on SourceForge in an effort to understand trends in programming language usage in the Open Source community between 2000 and 2005. The trends we consider include: 1) the relative popularity of the ten most popular programming languages over time, 2) the use of multiple programming languages by individual programmers and by individual projects, and 3) the programming languages most often used in combination.}, keywords = {cvs, cvs2mysql, programming languages, sfra, sourceforge, srda}, attachments = {https://flosshub.org/sites/flosshub.org/files/Delorey2007b.pdf}, author = {Delorey, Daniel P. and Knutson, Charles D. and Giraud-Carrier, C.} } @conference {672, title = {Project Entity Matching across FLOSS Repositories}, booktitle = {OSS2007: Open Source Development, Adoption and Innovation (IFIP 2.13)}, series = {IFIP International Federation for Information Processing }, volume = {234/2007}, year = {2007}, month = {2007///}, pages = {45 - 57}, publisher = {Springer}, organization = {Springer}, chapter = {4}, abstract = {Much of the data about free, libre, and open source (FLOSS) software development comes from studies of code repositories used for managing projects. This paper presents a method for integrating data about open source projects by way of matching projects (entities) and deleting duplicates across multiple code repositories. After a review of the relevant literature, a few of the methods are chosen and applied to the FLOSS domain, including a simple scoring system for confidence in pairwise project matches. Finally, the paper describes limitations of this approach and recommendations for future work. }, issn = {978-0-387-72485-0}, doi = {http://dx.doi.org/10.1007/978-0-387-72486-7_4}, attachments = {https://flosshub.org/sites/flosshub.org/files/Project\%20Entity\%20Matching.pdf}, author = {Conklin, Megan} } @article {flosswp367, title = {Promoting the Penguin: Who is Advocating Open Source Software in Commercial Settings?}, year = {2007}, month = {August}, abstract = {Most firms that use or develop software today face the questions of whether and how to engage in open source software. Yet, little is known about the process of OSS adoption and diffusion within corporations. Guided by the theoretical frameworks of Rogers (innovation diffusion) and Davis (Technology Acceptance Model), we develop a model of how job function influences individuals??? proclivity to support their employers??? adoption of OSS and OSS practices. We argue that job function determines which tasks in the software development process are part of an individual???s daily routine, and that different tasks are differentially affected by OSS. Our study is based on interviews with 25 individuals and a large-scale survey distributed to 249 participants in the telecommunications department of a multinational company. The results, although consistent with theoretical considerations, are nevertheless surprising. Distinguishing between developers, software testers, software architects, project managers, and managers, we find greater involvement in OSS activities to be favored most strongly by software testers, followed by software architects and managers. Excepting project managers, developers, despite having the most experience with OSS, are the least favorably disposed to greater corporate engagement in OSS. A corporation interested in adopting OSS and open innovation processes should thus take into account the job function-related incentives of each individual as well as various organizational factors. More generally, we propose that models developed to predict IT adoption behavior be extended to account for the ways in which individual adopters interact with the innovation at hand, which we maintain will be determined largely by their job functions.}, attachments = {https://flosshub.org/sites/flosshub.org/files/Alexy_Henkel_-_Promoting_the_Penguin.pdf}, author = {Oliver Alexy and Joachim Henkel} } @article {flosswp369, title = {Putting a Value on Openness: The Effect of Product Source Code Releases on the Market Value of Firms}, year = {2007}, month = {October}, abstract = {This study examines the effect of releasing the source code of commercial software products as open source software on the market value of firms. Using a sample of 30 software companies in the time span from 1 January 1999 to 30 April 2007, I find that market valuation is influenced by investor sentiment???abnormal returns take a curvilinear shape over time???and the business model firms choose for their OSS efforts???non-existence of an explicit revenue model is punished by the capital market. From my findings, I deduce several implications for IT-related event studies and research on open innovation processes.}, attachments = {https://flosshub.org/sites/flosshub.org/files/Alexy_-_Putting_a_Value_on_Openness.pdf}, author = {Oliver Alexy and Joachim Henkel} } @conference {703, title = {Participation in Free and Open Source Communities: An Empirical Study of Community Members{\textquoteright} Perceptions}, booktitle = {OSS2006: Open Source Systems (IFIP 2.13)}, series = {IFIP International Federation for Information Processing}, year = {2006}, pages = {221 - 231}, publisher = {Springer}, organization = {Springer}, abstract = {Although the defining factors of Free and Open Source Software (FOSS) are generally seen as the availability and accessibility of the source code, it is what these facilitate that is perhaps of more significance. Source code availability allows the sharing of code, skills, knowledge, and effort, focused on a particular piece of software under development. The result of this is the FOSS community, which although often perceived as a single group, is actually many small groups, each bound by a common interest in a particular piece of software and using the Internet as a communication medium. Although there have been studies focusing on the motivation of FOSS developers to contribute to software, there has been little investigation into the motives, attitudes, and the culture within the communities as a whole. There is much more to most of these communities than software development. Many also have extensive support networks for the use of software, portals for research, and social facilities. This paper describes the results of an investigation into how FOSS community members perceive the communities that they belong to, their reasons for being in the community, and the manner in which they participate. }, keywords = {Survey}, doi = {http://dx.doi.org/10.1007/0-387-34226-5_22}, attachments = {https://flosshub.org/sites/flosshub.org/files/Participation\%20in\%20free\%20and\%20open\%20source.pdf}, author = {Schofield, Andrew and Cooper, Grahame} } @conference {704, title = {Perceptions and Uptake of Open Source in Swedish Organisations}, booktitle = {OSS2006: Open Source Systems (IFIP 2.13)}, series = {IFIP International Federation for Information Processing}, year = {2006}, pages = {155 - 163}, publisher = {Springer}, organization = {Springer}, abstract = {There are many different ways in which Open Source ideas can be adopted by business, and influence the way in which companies do business. A number of different surveys have been conducted in different countries with the purpose of understanding the state of practice with respect to Open Source in companies. A number of different business models have been observed, ranging from the use of Open Source infrastructure products to basing a company{\textquoteright}s entire business model on Open Source. In this paper we report on a study of the perceptions of Open Source and the uptake of open source products and development models in Swedish companies. We investigate this from the standpoint of stakeholders in those companies which have an expressed interest in Open Source, allowing a more in-depth analysis of the extent to which Open Source has influenced business thinking. From our analysis we find that uptake is much higher than reported in earlier studies, but is still concentrated in SMEs, consistent with the findings of previous studies. There is increased evidence of interest beyond the simple use of OS components at the (LAMP) infrastructure level. In particular, a significant proportion of the companies are in a symbiotic relationship with the OS community, supporting both through participation in existing projects and the release of new software under OS licences. }, doi = {http://dx.doi.org/10.1007/0-387-34226-5_15}, attachments = {https://flosshub.org/sites/flosshub.org/files/Perceptions\%20and\%20Uptake\%20of\%20Open\%20Source.pdf}, author = {Lundell, Bj{\"o}rn and Lings, Brian and Lindqvist, Edvin} } @conference {Knab:2006:PDD:1137983.1138012, title = {Predicting defect densities in source code files with decision tree learners}, booktitle = {Proceedings of the 2006 international workshop on Mining software repositories}, series = {MSR {\textquoteright}06}, year = {2006}, pages = {119{\textendash}125}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {With the advent of open source software repositories the data available for defect prediction in source files increased tremendously. Although traditional statistics turned out to derive reasonable results the sheer amount of data and the problem context of defect prediction demand sophisticated analysis such as provided by current data mining and machine learning techniques.In this work we focus on defect density prediction and present an approach that applies a decision tree learner on evolution data extracted from the Mozilla open source web browser project. The evolution data includes different source code, modification, and defect measures computed from seven recent Mozilla releases. Among the modification measures we also take into account the change coupling, a measure for the number of change-dependencies between source files. The main reason for choosing decision tree learners, instead of for example neural nets, was the goal of finding underlying rules which can be easily interpreted by humans. To find these rules, we set up a number of experiments to test common hypotheses regarding defects in software entities. Our experiments showed, that a simple tree learner can produce good results with various sets of input data.}, keywords = {change analysis, data mining, decision tree learner, defect density, defect prediction, mozilla, prediction, release history, scm, source code, version control}, isbn = {1-59593-397-2}, doi = {http://doi.acm.org/10.1145/1137983.1138012}, url = {http://doi.acm.org/10.1145/1137983.1138012}, attachments = {https://flosshub.org/sites/flosshub.org/files/119Predicting.pdf}, author = {Knab, Patrick and Pinzger, Martin and Bernstein, Abraham} } @article {flosswp347, title = {A preliminary examination of code review processes in open source projects}, year = {2006}, month = {January}, abstract = {In this paper, we provide preliminary answers to the following questions regarding OSS peer review or inspection. What is the patch process and review process used by the projects? What types of review does a the project use? Why are patches rejected? What percentage of patches are rejected? Who performs the review? Are the top developers also the top reviewers? When are reviews performed? What is the frequency of review? How long do reviews take to perform? How does the patch size affect the review? How does merit-based trust among actors affect the review? Are more trusted individuals reviewed less often? How much feedback is provided in the review? What kinds of non-source code patches are reviewed? How does the kind of patch affect the review? What affect does reviewing have on other elements of the patch process? What is the relationship between reviewing and testing? The first two questions are answered in a qualitative manner for GCC, Linux, Mozilla, and Apache. The remaining questions are answered for the Apache project. The most striking similarities among projects is there use of a pre-commit review and requests for small, complete, independent patches. The Apache project also uses a post-commit review of trusted members. Reviews in the Apache project occur very frequently and usually have a review interval of hours. A small core group of reviewers conduct over 80\% of reviews for Apache; however, the number of and actual individuals fluctuates over the 9 years of data we examine.}, attachments = {https://flosshub.org/sites/flosshub.org/files/Rigby2006TR.pdf}, author = {Peter C. Rigby and Daniel M. German} } @conference {705, title = {Producing and Interpreting Debug Texts}, booktitle = {OSS2006: Open Source Systems (IFIP 2.13)}, series = {IFIP International Federation for Information Processing }, volume = {203/2006}, year = {2006}, month = {2006///}, pages = {335 - 336}, publisher = {Springer}, organization = {Springer}, abstract = {This paper presents preliminary findings from an ethnographic study of distributed, parallel debugging in an open source software (OSS) community. Focusing on the OSS developers{\textquoteright} daily activities, I propose the concept of making software debuggable. In so doing, I see a somewhat different story than common narratives of debugging in current OSS research, which describes distributed, parallel debugging as a set of highly cohesive tasks within loosely couple groups. I find that parallel, distributed debugging is rather a closely coupled collective process of producing and interpreting debug texts with high cohesion between the activities of reporting, finding, and understanding bugs. }, issn = {978-0-387-34225-2}, doi = {http://dx.doi.org/10.1007/0-387-34226-5_34}, attachments = {https://flosshub.org/sites/flosshub.org/files/Producing\%20and\%20Interpreting\%20Debug\%20Texts.pdf}, author = {{\O}sterlie, Thomas} } @article {flosswp214, title = {Penguins, Camels, and Other Birds of a Feather: Brokerage, Boundary Spanning, and Leadership in Open Innovation Communities}, year = {2005}, month = {April}, abstract = {What types of human and social capital identify the emergence of leaders of open innovation communities? Consistent with the norms of an engineering culture, we find that future leaders must first make strong technical contributions. Beyond technical contributions, they must then integrate their voluntary communities in order to avoid the ever present danger of forking and balkanization. This is enabled by two correlated but distinct social positions: brokerage, and boundary spanning between technological modules. An inherent lack of trust associated with brokerage positions can be overcome through physical interaction or contributions within technological boundaries. Successful leaders are thus the product of strong technical contribution and a structural position that can bind the community together.}, attachments = {https://flosshub.org/sites/flosshub.org/files/flemingwaguespack.pdf}, author = {Lee Fleming} } @conference {Phadke:2005:PRM:1145319.1145337, title = {Predicting risky modules in open-source software for high-performance computing}, booktitle = {Proceedings of the second international workshop on Software engineering for high performance computing system applications}, series = {SE-HPCS {\textquoteright}05}, year = {2005}, pages = {60{\textendash}64}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {This paper presents the position that software-quality modeling of open-source software for high-performance computing can identify modules that have a high risk of bugs.Given the source code for a recent release, a model can predict which modules are likely to have bugs, based on data from past releases. If a user knows which software modules correspond to functionality of interest, then risks to operations become apparent. If the risks are too great, the user may prefer not to upgrade to the most recent release.Of course, such predictions are never perfect. After release, bugs are discovered. Some bugs are missed by the model, and some predicted errors do not occur. A successful model will be accurate enough for informed management action at the time of the predictions.As evidence for this position, this paper summarizes a case study of the Portable Extensible Toolkit for Scientific Computation (PETSC), which is a mathematical library for high-performance computing. Data was drawn from source-code and configuration management logs. The accuracy of logistic-regression and decision-tree models indicated that the methodology is promising. The case study also illustrated several modeling issues.}, keywords = {C4.5, decision trees, empirical case study, high performance computing, logistic regression, Open-source software, PETSc, software metrics, software quality model, software reliability}, isbn = {1-59593-117-1}, doi = {10.1145/1145319.1145337}, url = {http://doi.acm.org/10.1145/1145319.1145337}, author = {Phadke, Amit A. and Allen, Edward B.} } @conference {Stewart:2005:PAI:1042438.1043100, title = {A Preliminary Analysis of the Influences of Licensing and Organizational Sponsorship on Success in Open Source Projects}, booktitle = {Proceedings of the Proceedings of the 38th Annual Hawaii International Conference on System Sciences - Volume 07}, series = {HICSS {\textquoteright}05}, year = {2005}, note = {"Publicly available data on open source projects registered on the Freshmeat website (www.freshmeat.net) was used to test the hypotheses. Data was collected from each project{\textquoteright}s Freshmeat website at the start and end of an eight month period (March - December 2002)." "We first selected three project categories from which to draw our sample. These were utilities, software development, and games." "Within these categories we further differentiated between new projects, which had been registered on the site within the two weeks prior to our first data collection point and older projects that had been registered more than two weeks prior to our initial data collection." }, month = {2005}, pages = {1-10}, publisher = {IEEE Computer Society}, organization = {IEEE Computer Society}, address = {Washington, DC, USA}, abstract = {This paper develops and tests a model of the impact of licensing restrictiveness and organizational sponsorship on the popularity and vitality of open source software (OSS) development projects. Using data gathered from Freshmeat.net and OSS project home pages the main conclusions derived from the analysis are that organizational sponsorship has a positive effect on project popularity by easing user concerns about cost and quality and that license restrictiveness may have a negative effect on popularity by reducing the perceived utility of open source software. Theoretical and practical implications are discussed, and the paper outlines several avenues for future research.}, keywords = {contributors, developers, freshmeat, license analysis, licensing, metadata, popularity, restrictive, users}, isbn = {0-7695-2268-8-7}, doi = {http://dx.doi.org/10.1109/HICSS.2005.38}, url = {http://dx.doi.org/10.1109/HICSS.2005.38}, author = {Stewart, Katherine J. and Ammeter, Anthony P. and Maruping, Likoebe M.} } @conference {764, title = {Principles for a Dynamic Software Ecosystem}, booktitle = {OSS2005: Open Source Systems }, year = {2005}, pages = {267}, abstract = {The open source software movement reflects one of the most dramatic developments in today{\textquoteright}s dynamic information technology industry. Interestingly, some commentators have sought to posit open source against proprietary software. This paper argues that while open source and proprietary models may be based on different development and distribution philosophies, neither model is inherently superior.}, url = {http://pascal.case.unibz.it/handle/2038/1424}, author = {M{\"u}ller, Beno{\^\i}t} } @article {898, title = {Process Modeling Across the Web Information Infrastructure}, journal = {Software Process--Improvement and Practice}, volume = {10}, number = {3}, year = {2005}, month = {July-September}, pages = {255-272}, author = {Chris Jensen and Walt Scacchi} } @conference {757, title = {Proprietary Software and Open Source Philosophy: a shift in software{\textquoteright}s production methods}, booktitle = {OSS2005: Open Source Systems }, year = {2005}, pages = {237-240}, abstract = {The aim of this paper is to point out that, since the massive growth of Open Source Software (OSS), the production methods of software have changed. The change is not only recognisable within the OSS communities but most evident effects can be also observed in the {\textquotedblleft}proprietary{\textquotedblright} segment of the market. The data analysis has been performed by allocating a variation towards or away from cooperation/ competition according to the direction of about 12,000 communications, articles and technical notes dated from 1998 up to February 2005. A co-evolution path is identifiable: both the OSS and the proprietary models interchange their original market and production strategies. In the case of the OSS segment, market strategies becomes more business oriented; as a result, systems previously based solely on remote users/producers relations exchange some of the redundancy in its process in favour of a more businessdriven and coordinated production process. On the other hand, proprieta...}, url = {ttp://pascal.case.unibz.it/handle/2038/1425}, author = {De Prato, Giuditta and Gagliardi, Dimitri} } @article {flosswp202, title = {The Provision of a Public Good with a direct Provision Technology and Large Number of Agents}, year = {2005}, month = {January}, abstract = {This paper provides a limit result for the provision of a public good in a mechanism design framework as the number of agents gets large. A canonical example for a public good that is produced with a direct provision technology is Open Source Software.}, attachments = {https://flosshub.org/sites/flosshub.org/files/behringer.pdf}, author = {Stefan Behringer} } @article {flosswp185, title = {Papers from Anthropological Quarterly (Vol 77, No 3) - Social Thought and Commentary: Culture{\textquoteright}s Open Source}, year = {2004}, month = {October}, abstract = {Listing of papers: Christopher M. Kelty | Culture{\textquoteright}s Open Sources: Software, Copyright, and Cultural Critique {\textendash}- Gabriella Coleman | The Political Agnosticism of Free and Open Source Software and the Inadvertent Politics of Contrast {\textendash}- Alex Golub | Copyright and Taboo {\textendash}- Anita Chan | Coding Free Software, Coding Free States: Free Software Legislation and the Politics of Code in Peru{\textendash}- Christopher M. Kelty | Punt To Culture{\textendash}- Rosemary J. Coombe \& Andrew Herman | Rhetorical Virtues: Property, Speech, and the Commons on the World-Wide Web{\textendash}- Glenn Otis Brown | Commentary}, attachments = {https://flosshub.org/sites/flosshub.org/files/aq_cultures_opensources.pdf}, author = {Christoper Kelty} } @article {flosswp190, title = {Patterns of Free Revealing ? Balancing Code Sharing and Protection in Commercial Open Source Development}, year = {2004}, month = {September}, abstract = {Commercial firms increasingly contribute to the development of open source software (OSS). However, a conflict often arises between the requirements of the General Public License to make "derived work" available, and firms? interest to protect their intellectual property embodied in the code. If there are ways to mitigate or solve this conflict, the conditions under which OSS will be an appealing solution to firms become much more general. This paper is the first to provide a quantitative empirical study of this conflict and the ways firms deal with it. I present a study of embedded Linux, based on an online-survey that yielded 268 valid responses. It turns out that firms routinely use various means to protect their developments, while keeping the GPL. Still, they do reveal a considerable share of their code? on average, 49\%. Heterogeneity between firms is analyzed using multivariate analysis. I show how the relative importance of various benefits and downsides of revealing determines a firm?s pattern of revealing. An analysis of reported reasons for revealing and of the type of code that is revealed provides further insights into these patterns. Putting the different dimensions of revealing behavior together, I find that consistent patterns of revealing can be identified for different types of firms.}, attachments = {https://flosshub.org/sites/flosshub.org/files/henkel2.pdf}, author = {Joachim Henkel} } @proceedings {flosswp181, title = {The perils and pitfalls of mining SourceForge}, year = {2004}, month = {05/2004}, pages = {7-11}, abstract = {SourceForge provides abundant accessible data from Open Source Software development projects, making it an attractive data source for software engineering research. However it is not without theoretical peril and practical pitfalls. In this paper, we outline practical lessons gained from our spidering, parsing and analysis of SourceForge data. SourceForge can be practically difficult: projects are defunct, data from earlier systems has been dumped in and crucial data is hosted outside SourceForge, dirtying the retrieved data. These practical issues play directly into analysis: decisions made in screening projects can reduce the range of variables, skewing data and biasing correlations. SourceForge is theoretically perilous: because it provides easily accessible data items for each project, tempting researchers to fit their theories to these limited data. Worse, few are plausible dependent variables. Studies are thus likely to test the same hypotheses even if they start from different theoretical bases. To avoid these problems, analyses of SourceForge projects should go beyond project level variables and carefully consider which variables are used for screening projects and which for testing hypotheses.}, keywords = {Data Collection, sourceforge}, attachments = {https://flosshub.org/sites/flosshub.org/files/howison04msr.pdf}, author = {Howison, James and Kevin Crowston} } @article {42, title = {The Political Agnosticism of Free and Open Source Software and the Inadvertent Politics of Contrast}, journal = {Anthropological Quarterly}, volume = {77}, number = {3}, year = {2004}, pages = {507--519}, publisher = {The George Washington University Institute for Ethnographic Research}, isbn = {00035491}, url = {http://www.jstor.org/stable/3318232}, author = {Coleman, E.G.} } @unpublished {flosswp197, title = {Political Motives of Developers for Collaboration on GNU/Linux}, year = {2004}, month = {August}, abstract = {This paper examines to what degree developers of the collaboratively produced computer operating system GNU/Linux are politically motivated for their contributions. It first states that software is politically relevant. It then goes on to argue for the political significance of Free Software/Open Source Software (FS/OSS) and discusses the developers ambivalent attitude towards a politicisation of FS/OSS. Centrepiece is a survey carried out with 85 GNU/Linux developers that showed that most of them are conscious of the social relevance of FS/OSS and that their engagement is of a deliberately political nature.}, attachments = {https://flosshub.org/sites/flosshub.org/files/escher.pdf}, author = {Tobias Escher} } @article {1077, title = {Profiling an Open Source Project Ecology and Its Programmers}, journal = {Electronic Markets}, volume = {14}, year = {2004}, month = {6/2004}, pages = {77 - 88}, abstract = {While many successful and well-known open source projects produce output of high quality, a general assessment of this development paradigm is still missing. In this paper, an online community of both small and large, successful and failed projects and their programmers is analysed mainly using the version-control data of each project, also according to their productivity and estimation of expended effort. As the results show, there are indeed significant differences between this cooperative development model and the commercial organization of work in the areas explored. Both open source software projects in their size and their programmers{\textquoteright} effort differ significantly, and the evolution of projects{\textquoteright} size over time seems in part to contradict the laws of software evolution proposed for commercial systems. Both the inequality of effort distribution between programmers and an increasing number of developers in a project do not lead to a decrease in productivity, opposing Brooks{\textquoteright}s Law. Effort estimation based on the COCOMO model for commercial organizations shows a large amount of effort expended for the projects, while a more general Norden-Rayleigh modeling shows a distinctly smaller expenditure. This proposes that either a highly efficient development is achieved by this self-organizing cooperative and highly decentralized form of work, or that the participation of users besides programming tasks is enormous and constitutes an economic factor of large proportions. }, keywords = {affiliation network, brooks law, cocomo, effort estimation, evolution, productivity, project success, scm, size, time, version control}, issn = {1422-8890}, doi = {10.1080/10196780410001675031}, author = {Koch, Stefan} } @article {flosswp97, title = {Participatory Usability: supporting proactive users}, journal = {Proceedings of the 4th Annual Conference of the ACM Special Interest Group on Computer Human Interaction - New Zealand Chapter (CHINZ{\textquoteright}03)}, year = {2003}, month = {June}, pages = {63{\textendash}68}, publisher = {ACM SIGCHI New Zealand.}, abstract = {After software has been released the opportunities for users to influence development can often be limited. In this paper we review the research on post-deployment usability and make explicit its connections to open source software development. We describe issues involved in the design of end-user reporting tools with reference to the Safari web browser and a digital library prototype.}, attachments = {https://flosshub.org/sites/flosshub.org/files/nicholsmckaytwidale.pdf}, author = {David M Nichols and Dana McKay and Michael B Twidale} } @unpublished {flosswp86, title = {Puzzling with a top-down Blueprint and a bottom-up Network: An explorative analysis of the Open Source World using ITIL and Social Network Analysis}, year = {2003}, month = {February}, abstract = {This paper explains some of the necessary tasks that need to be performed for the construction and maintenance of software. These necessary activities are abstracted from ITIL, a best- practice {\textquoteright}blueprint{\textquoteright}, that is often used by IT companies to structure their processes. Next, using Social Network Analysis, an investigation is conducted to asses how the activities that ITIL describes are performed in the open source {\textquoteright}network{\textquoteright}.}, attachments = {https://flosshub.org/sites/flosshub.org/files/meerman2.pdf}, author = {Sanne Te Meerman} } @article {flosswp56, title = {Permanently Beta: Responsive Organization in the Internet Era}, year = {2002}, month = {September}, abstract = {How has the process of technological change in the Internet era influenced the way we organize economic activities? In this paper we discuss how information technologies foster the emergent design and user-driven design of websites and other online media, as well as products and organizations offline. A cycle of testing, feedback, and innovation facilitates ongoing negotiations around making products and around organizing that production. We call the organizational state of flux that emerges from these negotiations Permanently Beta. Beta testing, open source software, and interactive communities manifest aspects of permanently beta organization.}, attachments = {https://flosshub.org/sites/flosshub.org/files/neff-stark.pdf}, author = {Gina Neff} } @conference {Dinkelacker:2002:POS:581339.581363, title = {Progressive open source}, booktitle = {Proceedings of the 24th International Conference on Software Engineering}, series = {ICSE {\textquoteright}02}, year = {2002}, pages = {177{\textendash}184}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {The success of several Open Source{\texttrademark} software systems, e.g., Apache, Bind, Emacs, and Linux, has recently sparked interest in studying and emulating the software engineering principles underlying this innovative development and use model. Certain aspects of the Open Source development method, e.g., community building, open discussions for requirements and features, and evolvable and modular designs are having fundamental and far reaching consequences on general software engineering practices.To leverage such Open Source methods and tools, we have defined an innovative software engineering paradigm for large corporations: Progressive Open Source (POS). POS leverages the power of Open Source methods and tools for large corporations in a progressive manner: starting from completely within the corporation, to include partner businesses, and eventually complete Open Source. In this paper we present the design goals and principles for POS. We illustrate POS with two programs in HP: Corporate Source and the Collaborative Development Program (CDP). We present early results from both these programs suggesting the power and necessity of POS for all modern large corporations.}, keywords = {companies}, isbn = {1-58113-472-X}, doi = {10.1145/581339.581363}, url = {http://doi.acm.org/10.1145/581339.581363}, author = {Dinkelacker, Jamie and Garg, Pankaj K. and Miller, Rob and Nelson, Dean} } @article {flosswp62, title = {Protecting the Virtual Commons: self-organizing communities and innovative intellectual property rights regimes}, year = {2002}, month = {October}, abstract = {This paper discusses the tensions between open source communities and proprietary software development and identifies a number of innovative regimes that should deal with these tensions.}, attachments = {https://flosshub.org/sites/flosshub.org/files/joode.pdf}, author = {Rueben Van Wendel De Joode} } @article {flosswp70, title = {Public Subsidies for Open Source? Some Economic Policy Issues of the Software Market}, year = {2002}, month = {November}, abstract = {This paper discusses the economic merits of direct or indirect governmental support for open source projects. Software markets differ from standard textbook markets in three important respects that may give rise to market failures: (i) large economies of scale, (ii) crucially important innovations, (iii) significant network effects and switching costs. We analyze the differences between proprietary software and open source software with respect to these market features and ask whether open source as an alternative to proprietary software can mitigate these problems. Then we discuss the implications of various forms of governmental support for open source.}, attachments = {https://flosshub.org/sites/flosshub.org/files/schmidtschnitzer.pdf}, author = {Klaus Schmidt} } @article {flosswp33, title = {Peripheral Members in Online Communities}, year = {2001}, month = {Unspecified}, abstract = {Organizations are exploring the role communities play in knowledge management and online communities are attracting more and more attentions. One difference between online communities and conventional communities lies in the large number of peripheral members in online communities, which is the focus of the study. The study empirically verifies the important role peripheral members play in online communities. It also suggests that in addition to benefiting from online communities, peripheral members also contribute to online communities.}, attachments = {https://flosshub.org/sites/flosshub.org/files/zhang.pdf}, author = {Wei Zhang} } @article {flosswp34, title = {Positive Intellectual Rights and Information Exchanges}, year = {2001}, month = {July}, abstract = {This paper proposes a reversal in how to consider the rights associated with information, media contents, software and other intellectual entities. The proposed approach sets as its basis a number of positive intellectual rights, defined as to enable wide societal production and exchange of intellectual entities. It then defines how granting of specific attributes of property is necessary as to ensure that the positive rights are not abused to the detriment of some basic values, and are implemented in reality. Such a reversal allows to exploit the benefits of information and communication technology. More generally, it debates right issues for the technology of the intangible.}, attachments = {https://flosshub.org/sites/flosshub.org/files/aigrain.pdf , https://flosshub.org/sites/flosshub.org/files/aigrain_0.pdf}, author = {Philippe Aigrain} } @article {flosswp14, title = {The Political Economy of Open Source}, year = {2000}, month = {June}, abstract = {The paper describes the open source process and characterizes more fully the economic, technological, and social systems that together constitute this distinct mode of production. The paper explains the open source process, by answering three questions about individual motivations, coordination, and complexity using a compoud argument of microfoundations, economic logic, and social/political structure.}, attachments = {https://flosshub.org/sites/flosshub.org/files/wp140.pdf}, author = {Steven Weber} } @article {flosswp3, title = {Profiting From Voluntary Information Spillovers: How Users Benefit By Freely Revealing Their Innovations}, year = {2000}, month = {July}, abstract = {Software users reveal the code they have written to other users for free. This behavior is contrary to conventional wisdom in economics - but is essential to the functioning of an effective user innovation community. This paper explores conditions under which the free revealing of innovations (code, in the case of OS) pays for innovating users.}, attachments = {https://flosshub.org/sites/flosshub.org/files/evhippel-voluntaryinfospillover.pdf}, author = {Dietmar Harhoff and Joachim Henkel and von Hippel, Eric} }