@conference {Vasilescu:2016:SLM:2884781.2884875, title = {The Sky is Not the Limit: Multitasking Across GitHub Projects}, booktitle = {Proceedings of the 38th International Conference on Software Engineering (ICSE 2016)}, series = {ICSE {\textquoteright}16}, year = {2016}, pages = {994{\textendash}1005}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {Software development has always inherently required multitasking: developers switch between coding, reviewing, testing, designing, and meeting with colleagues. The advent of software ecosystems like GitHub has enabled something new: the ability to easily switch between projects. Developers also have social incentives to contribute to many projects; prolific contributors gain social recognition and (eventually) economic rewards. Multitasking, however, comes at a cognitive cost: frequent context-switches can lead to distraction, sub-standard work, and even greater stress. In this paper, we gather ecosystem-level data on a group of programmers working on a large collection of projects. We develop models and methods for measuring the rate and breadth of a developers{\textquoteright} context-switching behavior, and we study how context-switching affects their productivity. We also survey developers to understand the reasons for and perceptions of multitasking. We find that the most common reason for multitasking is interrelationships and dependencies between projects. Notably, we find that the rate of switching and breadth (number of projects) of a developer{\textquoteright}s work matter. Developers who work on many projects have higher productivity if they focus on few projects per day. Developers that switch projects too much during the course of a day have lower productivity as they work on more projects overall. Despite these findings, developers perceptions of the benefits of multitasking are varied. }, keywords = {github, multitasking, productivity}, isbn = {978-1-4503-3900-1}, doi = {10.1145/2884781.2884875}, url = {http://doi.acm.org/10.1145/2884781.2884875}, author = {Vasilescu, Bogdan and Blincoe, Kelly and Xuan, Qi and Casalnuovo, Casey and Damian, Daniela and Devanbu, Premkumar and Filkov, Vladimir} } @conference {Robles:2014:FSD:2597073.2597129, title = {FLOSS 2013: A Survey Dataset About Free Software Contributors: Challenges for Curating, Sharing, and Combining}, booktitle = {Proceedings of the 11th Working Conference on Mining Software Repositories}, series = {MSR 2014}, year = {2014}, pages = {396{\textendash}399}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {In this data paper we describe a data set obtained by means of performing an on-line survey to over 2,000 Free Libre Open Source Software (FLOSS) contributors. The survey includes questions related to personal characteristics (gender, age, civil status, nationality, etc.), education and level of English, professional status, dedication to FLOSS projects, reasons and motivations, involvement and goals. We describe as well the possibilities and challenges of using private information from the survey when linked with other, publicly available data sources. In this regard, an example of data sharing will be presented and legal, ethical and technical issues will be discussed. }, keywords = {anonymization, data combining, data sharing, ethics, free software, microdata, msr data showcase, open data, open source, privacy, Survey}, isbn = {978-1-4503-2863-0}, doi = {10.1145/2597073.2597129}, url = {http://doi.acm.org/10.1145/2597073.2597129}, attachments = {https://flosshub.org/sites/flosshub.org/files/msr14gregorio.pdf}, author = {Gregorio Robles and Reina, Laura Arjona and Serebrenik, Alexander and Vasilescu, Bogdan and Gonz{\'a}lez-Barahona, Jes{\'u}s M.} } @conference {Vasilescu:2014:SQS:2531602.2531659, title = {How Social Q\&A Sites Are Changing Knowledge Sharing in Open Source Software Communities}, booktitle = {Proceedings of the 17th ACM Conference on Computer Supported Cooperative Work \&\#38; Social Computing}, series = {CSCW {\textquoteright}14}, year = {2014}, pages = {342{\textendash}354}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {Historically, mailing lists have been the preferred means for coordinating development and user support activities. With the emergence and popularity growth of social Q\&A sites such as the StackExchange network (e.g., StackOverflow), this is beginning to change. Such sites offer different socio-technical incentives to their participants than mailing lists do, e.g., rich web environments to store and manage content collaboratively, or a place to showcase their knowledge and expertise more vividly to peers or potential recruiters. A key difference between StackExchange and mailing lists is gamification, i.e., StackExchange participants compete to obtain reputation points and badges. In this paper, we use a case study of R (a widely-used tool for data analysis) to investigate how mailing list participation has evolved since the launch of StackExchange. Our main contribution is the assembly of a joint data set from the two sources, in which participants in both the texttt{r-help} mailing list and StackExchange are identifiable. This permits their activities to be linked across the two resources and also over time. With this data set we found that user support activities show a strong shift away from texttt{r-help}. In particular, mailing list experts are migrating to StackExchange, where their behaviour is different. First, participants active both on texttt{r-help} and on StackExchange are more active than those who focus exclusively on only one of the two. Second, they provide faster answers on StackExchange than on texttt{r-help}, suggesting they are motivated by the emph{gamified} environment. To our knowledge, our study is the first to directly chart the changes in behaviour of specific contributors as they migrate into gamified environments, and has important implications for knowledge management in software engineering.}, keywords = {a, crowdsourced knowledge, gamification., mailing lists, open source, social q\&\#38}, isbn = {978-1-4503-2540-0}, doi = {10.1145/2531602.2531659}, url = {http://doi.acm.org/10.1145/2531602.2531659}, attachments = {https://flosshub.org/sites/flosshub.org/files/cscw14.pdf}, author = {Vasilescu, Bogdan and Serebrenik, Alexander and Devanbu, Prem and Filkov, Vladimir} } @conference {Gousios:2014:LGG:2597073.2597126, title = {Lean GHTorrent: GitHub Data on Demand}, booktitle = {Proceedings of the 11th Working Conference on Mining Software Repositories}, series = {MSR 2014}, year = {2014}, pages = {384{\textendash}387}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {In recent years, GitHub has become the largest code host in the world, with more than 5M developers collaborating across 10M repositories. Numerous popular open source projects (such as Ruby on Rails, Homebrew, Bootstrap, Django or jQuery) have chosen GitHub as their host and have migrated their code base to it. GitHub offers a tremendous research potential. For instance, it is a flagship for current open source development, a place for developers to showcase their expertise to peers or potential recruiters, and the platform where social coding features or pull requests emerged. However, GitHub data is, to date, largely underexplored. To facilitate studies of GitHub, we have created GHTorrent, a scalable, queriable, offline mirror of the data offered through the GitHub REST API. In this paper we present a novel feature of GHTorrent designed to offer customisable data dumps on demand. The new GHTorrent data-on-demand service offers users the possibility to request via a web form up-to-date GHTorrent data dumps for any collection of GitHub repositories. We hope that by offering customisable GHTorrent data dumps we will not only lower the "barrier for entry" even further for researchers interested in mining GitHub data (thus encourage researchers to intensify their mining efforts), but also enhance the replicability of GitHub studies (since a snapshot of the data on which the results were obtained can now easily accompany each study). }, keywords = {data on demand, dataset, github, msr data showcase}, isbn = {978-1-4503-2863-0}, doi = {10.1145/2597073.2597126}, url = {http://doi.acm.org/10.1145/2597073.2597126}, attachments = {https://flosshub.org/sites/flosshub.org/files/lean-ghtorrent_0.pdf}, author = {Gousios, Georgios and Vasilescu, Bogdan and Serebrenik, Alexander and Zaidman, Andy} } @conference {Pletea:2014:SES:2597073.2597117, title = {Security and Emotion: Sentiment Analysis of Security Discussions on GitHub}, booktitle = {Proceedings of the 11th Working Conference on Mining Software Repositories}, series = {MSR 2014}, year = {2014}, pages = {348{\textendash}351}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {Application security is becoming increasingly prevalent during software and especially web application development. Consequently, countermeasures are continuously being discussed and built into applications, with the goal of reducing the risk that unauthorized code will be able to access, steal, modify, or delete sensitive data. In this paper we gauged the presence and atmosphere surrounding security-related discussions on GitHub, as mined from discussions around commits and pull requests. First, we found that security related discussions account for approximately 10\% of all discussions on GitHub. Second, we found that more negative emotions are expressed in security-related discussions than in other discussions. These findings confirm the importance of properly training developers to address security concerns in their applications as well as the need to test applications thoroughly for security vulnerabilities in order to reduce frustration and improve overall project atmosphere. }, keywords = {github, mining challenge, msr challenge, security, sentiment analysis}, isbn = {978-1-4503-2863-0}, doi = {10.1145/2597073.2597117}, url = {http://doi.acm.org/10.1145/2597073.2597117}, attachments = {https://flosshub.org/sites/flosshub.org/files/pletea.pdf}, author = {Pletea, Daniel and Vasilescu, Bogdan and Serebrenik, Alexander} }