Computer Science

Shift scheduling impacts healthcare workers' well-being because it sets the frame for their social life and recreational activities. Since it is complex and time-consuming, it has become a target for automation. However, existing systems mostly focus on improving efficiency. The workers' needs and their active participation do not play a pronounced role. Contrasting this trend, we designed a social practice-based, worker-centered, and well-being-oriented self-scheduling system which gives healthcare workers more control during shift planning. In a following nine month appropriation study, we found that workers who were cautious about their social standing in the group or who had a more spontaneous personal lifestyle used our system less often than others. Moreover, we revealed several conflict prevention practices and suggest to shift the focus away from a competitive shift distribution paradigm towards supporting these pro-social practices. We conclude with guidelines to support individual planning practices, self-leadership, and for dealing with conflicts.

Major depressive disorder is a debilitating disease affecting 264 million people worldwide. While many antidepressant medications are available, few clinical guidelines support choosing among them. Decision support tools (DSTs) embodying machine learning models may help improve the treatment selection process, but often fail in clinical practice due to poor system integration. We use an iterative, co-design process to investigate clinicians' perceptions of using DSTs in antidepressant treatment decisions. We identify ways in which DSTs need to engage with the healthcare sociotechnical system, including clinical processes, patient preferences, resource constraints, and domain knowledge. Our results suggest that clinical DSTs should be designed as multi-user systems that support patient-provider collaboration and offer on-demand explanations that address discrepancies between predictions and current standards of care. Through this work, we demonstrate how current trends in explainable AI may be inappropriate for clinical environments and consider paths towards designing these tools for real-world medical systems.

Building on game design and education research, this paper introduces narrative-focused role-playing games as a way to promote visualization literacy in young children. Visualization literacy skills are vital in understanding the world around us and constructing meaningful visualizations, yet, how to better develop these skills at an early age remains largely overlooked and understudied. Only recently has the visualization community started to fill this gap, resulting in preliminary studies and development of educational tools for use in early education. We add to these efforts through the exploration of gamification to support learning, and identify an opportunity to apply role-playing game-based designs by leveraging the presence of narratives in data-related problems involving visualizations. We study the effects of including narrative elements on learning through a technology probe, grounded in a set of design considerations stemming from visualization, game design, and education science. We create two versions of a game -- one with narrative elements and one without -- and evaluate our instances on 33 child participants between 11- to 13-years old using a between-subjects study design. Despite participants requiring double the amount of time to complete their game due to additional elements, the inclusion of such elements were found to improve engagement without sacrificing learning; our results indicate no significant differences in development of graph-reading skills, but significant differences in engagement and overall enjoyment of the game. We report observations and qualitative feedback collected, and note areas for improvement and room for future wook.

Nowadays, automation not only permeates industry but also becomes a substantial part of our private, everyday lives. Driven by the idea of increased convenience and more time for the "important things in life," automation relieves us from many daily chores - robots vacuum floors and automated coffee makers produce supposedly barista-quality coffee on the press of a button. In many cases, these offers are embraced by people without further questioning. However, while we save time by delegating more and more everyday activities to automation, we also may lose chances for enjoyable and meaningful experiences. In two field studies, we demonstrate that a manual process has experiential benefits over more automated processes by using the example of coffee-making. We present a way to account for potential experiential costs of everyday automation and strategies of how to design interaction with automation to reconcile experience with the advantages of a more and more powerful automation.

Ambiguity, an information state where multiple interpretations are plausible, is a common challenge in visual analytics (VA) systems. We discuss lessons learned from a case study designing VA tools for Canadian avalanche forecasters. Avalanche forecasting is a complex and collaborative risk-based decision-making and analysis domain, demanding experience and knowledge-based interpretation of human reported and uncertain data. Differences in reporting practices, organizational contexts, and the particularities of individual reports result in a variety of potential interpretations that have to be negotiated as part of the forecaster's sensemaking processes. We describe our preliminary research using glyphs to support sensemaking under ambiguity. Ambiguity is not unique to public avalanche forecasting. There are many other domains where the way data are measured and reported vary in ways not accounted explicitly in the data and require analysts to negotiate multiple potential meanings. We argue that ambiguity is under-served by visualization research and would benefit from more explicit VA support.

A paper presented at the Workshop on Contestability in Algorithmic Systems at CSCW 2019. Challenging algorithmic decisions is important to decision subjects, yet numerous factors can limit a person's ability to contest such decisions. We propose that administrative law systems, which were created to ensure that governments are kept accountable for their actions and decision making in relation to individuals, can provide guidance on how to design contestation systems for algorithmic decision-making.

As pervasive data collection and powerful algorithms increasingly shape children's experience of the world and each other, their ability to interrogate computational algorithms has become crucially important. A growing body of work has attempted to articulate a set of "literacies" to describe the intellectual tools that children can use to understand, interrogate, and critique the algorithmic systems that shape their lives. Unfortunately, because many algorithms are invisible, only a small number of children develop the literacies required to critique these systems. How might designers support the development of critical algorithmic literacies? Based on our experience designing two data programming systems, we present four design principles that we argue can help children develop literacies that allow them to understand not only how algorithms work, but also to critique and question them.

This paper describes the development needed to support the functional and teaching requirements of iRead, a 4-year EU-funded project which produced an award-winning serious game utilising lexical and syntactical game content. The main functional requirement was that the game should retain different profiles for each student, encapsulating both the respective language model (which language features should be taught/used in the game first, before moving on to more advanced ones) and the user model (mastery level for each feature, as reported by the student's performance in the game). In addition to this, researchers and stakeholders stated additional requirements related to learning objectives and strategies to make the game more interesting and successful; these were implemented as a set of selection rules which take into account not only the mastery level for each feature, but also respect the priorities set by teachers, helping avoid repetition of content and features, and maintaining a balance between new content and revision of already mastered features to give students the sense of progress, while also reinforcing learning.

With rapid developments in consumer-level head-mounted displays and computer graphics, immersive VR has the potential to take online and remote learning closer to real-world settings. However, the effects of such digital transformations on learners, particularly for VR, have not been evaluated in depth. This work investigates the interaction-related effects of sitting positions of learners, visualization styles of peer-learners and teachers, and hand-raising behaviors of virtual peer-learners on learners in an immersive VR classroom, using eye tracking data. Our results indicate that learners sitting in the back of the virtual classroom may have difficulties extracting information. Additionally, we find indications that learners engage with lectures more efficiently if virtual avatars are visualized with realistic styles. Lastly, we find different eye movement behaviors towards different performance levels of virtual peer-learners, which should be investigated further. Our findings present an important baseline for design decisions for VR classrooms.

Crowdsourcing can collect many diverse ideas by prompting ideators individually, but this can generate redundant ideas. Prior methods reduce redundancy by presenting peers' ideas or peer-proposed prompts, but these require much human coordination. We introduce Directed Diversity, an automatic prompt selection approach that leverages language model embedding distances to maximize diversity. Ideators can be directed towards diverse prompts and away from prior ideas, thus improving their collective creativity. Since there are diverse metrics of diversity, we present a Diversity Prompting Evaluation Framework consolidating metrics from several research disciplines to analyze along the ideation chain - prompt selection, prompt creativity, prompt-ideation mediation, and ideation creativity. Using this framework, we evaluated Directed Diversity in a series of a simulation study and four user studies for the use case of crowdsourcing motivational messages to encourage physical activity. We show that automated diverse prompting can variously improve collective creativity across many nuanced metrics of diversity.