Previous research has revealed that newcomer women are disproportionately affected by gender-biased barriers in open source software (OSS) projects. However, this research has focused mainly on social/cultural factors, neglecting the software tools and infrastructure. To shed light on how OSS tools and infrastructure might factor into OSS barriers to entry, we conducted two studies: (1) a field study with five teams of software professionals, who worked through five use cases to analyze the tools and infrastructure used in their OSS projects; and (2) a diary study with 22 newcomers (9 women and 13 men) to investigate whether the barriers matched the ones identified by the software professionals. The field study produced a bleak result: software professionals found gender biases in 73 percent of all the newcomer barriers they identified. Further, the diary study confirmed these results: Women newcomers encountered gender biases in 63 percent of barriers they faced. Fortunately, many kinds of barriers and biases revealed in these studies could potentially be ameliorated through changes to the OSS software environments and tools.

Research has revealed that significant barriers exist when entering Open-Source Software (OSS) communities and that women disproportionately experience such barriers. However, this research has focused mainly on social/cultural factors, ignoring the environment itself --- the tools and infrastructure. To shed some light onto how tools and infrastructure might somehow factor into OSS barriers to entry, we conducted a field study with five teams of software professionals, who worked through five use-cases to analyze the tools and infrastructure used in their OSS projects. These software professionals found tool/infrastructure barriers in 7% to 71% of the use-case steps that they analyzed, most of which are tied to newcomer barriers that have been established in the literature. Further, over 80% of the barrier types they found include attributes that are biased against women.

How can we support software professionals who want to build human-adaptive sociotechnical systems? Building such systems requires skills some developers may lack, such as applying human-centric concepts to the software they develop and/or mentally modeling other people. Effective socio-technical methods exist to help, but most are manual and cognitively burdensome. In this paper, we investigate ways semi-automating a socio-technical method might help, using as our lens GenderMag, a method that requires people to mentally model people with genders different from their own. Toward this end, we created the GenderMag Recorder's Assistant, a semi-automated visual tool, and conducted a small field study and a 92-participant controlled study. Results of our investigation revealed ways the tool helped with cognitive load and ways it did not; unforeseen advantages of the tool in increasing participants' engagement with the method; and a few unforeseen advantages of the manual approach as well.

Personas often aim to improve product designers' ability to "see through the eyes of" target users through the empathy personas can inspire - but personas are also known to promote stereotyping. This tension can be particularly problematic when personas (who, of course as "people" have genders) are used to promote gender inclusiveness - because reinforcing stereotypical perceptions can run counter to gender inclusiveness. In this paper we explicitly investigate this tension through a new approach to personas: one that includes multiple photos (of males and females) for a single persona. We compared this approach to an identical persona with only one photo using a controlled laboratory study and an eye-tracking study. Our goal was to answer the following question: is it possible for personas to encourage product designers to engage with personas while at the same avoiding promoting gender stereotyping? Our results are encouraging about the use of personas with multiple pictures as a way to expand participants' consideration of multiple genders without reducing their engagement with the persona.

Foraging among similar variants of the same artifact is a common activity, but computational models of Information Foraging Theory (IFT) have not been developed to take such variants into account. Without being able to computationally predict people's foraging behavior with variants, our ability to harness the theory in practical ways--such as building and systematically assessing tools for people who forage different variants of an artifact--is limited. Therefore, in this paper, we introduce a new predictive model, PFIS-V, that builds upon PFIS3, the most recent of the PFIS family of modeling IFT in programming situations. Our empirical results show that PFIS-V is up to 25% more accurate than PFIS3 in predicting where a forager will navigate in a variationed information space.

Gender inclusiveness in computing settings is receiving a lot of attention, but one potentially critical factor has mostly been overlooked -- software itself. To help close this gap, we recently created GenderMag, a systematic inspection method to enable software practitioners to evaluate their software for issues of gender-inclusiveness. In this paper, we present the first real-world investigation of software practitioners' ability to identify gender-inclusiveness issues in software they create/maintain using this method. Our investigation was a multiple-case field study of software teams at three major U.S. technology organizations. The results were that, using GenderMag to evaluate software, these software practitioners identified a surprisingly high number of gender-inclusiveness issues: 25% of the software features they evaluated had gender-inclusiveness issues.

Foraging among too many variants of the same artifact can be problematic when many of these variants are similar. This situation, which is largely overlooked in the literature, is commonplace in several types of creative tasks, one of which is exploratory programming. In this paper, we investigate how novice programmers forage through similar variants. Based on our results, we propose a refinement to Information Foraging Theory (IFT) to include constructs about variation foraging behavior, and propose refinements to computational models of IFT to better account for foraging among variants.

Does socioeconomic status (SES) affect the way that end users use software? Previous work in inclusiveness, such as the recent work on gender-inclusiveness in software development, suggests that differences between populations can impact software use.

Recent research has reported numerous studies bringing into question the gender inclusiveness of many kinds of software. Inclusiveness of software (gender or otherwise) matters because supporting diversity matters - it is well-known that the more diverse a group of problem-solvers, the higher the quality of the solution. To help software creators identify features within their software that are not gender-inclusive, we recently created a method known as GenderMag. In this paper, we investigate the experience of teams of software professionals using GenderMag to find problems with software they are building. Our results show a high engagement with GenderMag personas - more than twice that of other personas research - and a very high degree of accuracy (93%) most of the time. Finally, our results pinpointed situations that we term “detours” that were especially prone to errors, with teams 6 times more likely to make errors in detours than they did otherwise.

Intelligent systems are gaining in popularity and receiving increased media attention, but little is known about how people actually go about developing them. In this paper, we attempt to fill this gap through a set of field interviews that investigate how people develop intelligent systems that incorporate machine learning algorithms. The developers we interviewed were experienced at working with machine learning algorithms and dealing with the large amounts of data needed to develop intelligent systems. Despite their level of experience, we learned that they struggle to establish a repeatable process. They described problems with each step of the processes they perform, as well as cross-cutting issues that pervade multiple steps of their processes. The unique difficulties that developers like these face seem to point to a need for software engineering advances that address such machine learning systems, and we conclude by discussing this need and some of its implications.

Developers performing maintenance activities must balance their efforts to learn the code vs. their efforts to actually change it. This balancing act is consistent with the “production bias” that, according to Carroll's minimalist learning theory, generally affects software users during everyday tasks. This suggests that developers' focus on efficiency should have marked effects on how they forage for the information they think they need to fix bugs. To investigate how developers balance fixing versus learning during debugging, we conducted the first empirical investigation of the interplay between production bias and information foraging. Our theory-based study involved 11 participants: half tasked with fixing a bug, and half tasked with learning enough to help someone else fix it. Despite the subtlety of difference between their tasks, participants foraged remarkably differently-making foraging decisions from different types of “patches,” with different types of information, and succeeding with different foraging tactics.