Homelessness systems in North America adopt coordinated data-driven approaches to efficiently match support services to clients based on their assessed needs and available resources. AI tools are increasingly being implemented to allocate resources, reduce costs and predict risks in this space. In this study, we conducted an ethnographic case study on the City of Toronto’s homelessness system’s data practices across different critical points. We show how the City’s data practices offer standardized processes for client care but frontline workers also engage in heuristic decision-making in their work to navigate uncertainties, client resistance to sharing information, and resource constraints. From these findings, we show the temporality of client data which constrain the validity of predictive AI models. Additionally, we highlight how the City adopts an iterative and holistic client assessment approach which contrasts to commonly used risk assessment tools in homelessness, providing future directions to design holistic decision-making tools for homelessness.
This paper explores pair collaboration as a novel approach for making sense of personal data. Pair collaboration---characterized by dyadic comparison and structured roles for questioning and reasoning---has proven effective for co-constructing knowledge. However, current collaborative visualization tools primarily focus on group comparisons, overlooking the challenges of accommodating pair collaboration in the context of personal data. To address this gap, we propose a set of design rationales supporting subjective data analysis through dyadic comparison and mixed-focus collaboration styles for co-constructing personal narratives. We operationalize these principles in a tangible visualization toolkit, \projectname. Our user study demonstrates that pairwise collaboration facilitated by the toolkit: 1) reveals detailed data insights that are effective for recalling personal experiences, and 2) fosters a structured, reciprocal sensemaking process for interpreting and reconstructing personal experiences beyond data insights. Our results shed light on the design rationales for, and the processes of pair sensemaking of personal data, and their effects to foster deep levels of reflection.
Data Humanism has gained prominence in personal visualization and Personal Informatics, advocating for a subjective and slow approach to engage with personal data. Collaborative sensemaking has great potential for aiding the understanding of personal data, yet little is known about addressing requirements of structure and coordination when integrating Data Humanism into collaborative visualization. In this paper, we propose design principles for creating both subjective and effective collaborative visualizations, while coordinating the slow sensemaking process and promoting data awareness and communication. We operationalize these principles into a personal visualization toolkit, which we evaluate with an observational study involving 16 university students (8 pairs) analyzing each other's screen-time data. Our findings reveal that implementing the proposed design principles: (1) facilitated data comparison from shared subjective perspectives, (2) helped coordinate sensemaking while allowing time for understanding personal data, and (3) helped the contextualization of data patterns, in turn aiding self-reflection.
Temporal predictive models have the potential to improve decisions in health care, public services, and other domains, yet they often fail to effectively support decision-makers. Prior literature shows that many misalignments between model behavior and decision-makers' expectations stem from issues of model specification, namely how, when, and for whom predictions are made. However, model specifications for predictive tasks are highly technical and difficult for non-data-scientist stakeholders to interpret and critique. To address this challenge we developed Tempo, an interactive system that helps data scientists and domain experts collaboratively iterate on model specifications. Using Tempo's simple yet precise temporal query language, data scientists can quickly prototype specifications with greater transparency about pre-processing choices. Moreover, domain experts can assess performance within data subgroups to validate that models behave as expected. Through three case studies, we demonstrate how Tempo helps multidisciplinary teams quickly prune infeasible specifications and identify more promising directions to explore.
Explanatory information helps users to evaluate the suggestions offered by AI-driven decision support systems. With large language models, adjusting explanation expressions has become much easier. However, how these expressions influence human decision-making remains largely unexplored. This study investigated the effect of explanation tone (e.g., formal or humorous) on decision-making, focusing on AI roles and user attributes. We conducted user experiments across three scenarios depending on AI roles (assistant, second-opinion provider, and expert) using datasets designed with varying tones. The results revealed that tone significantly influenced decision-making regardless of user attributes in the second-opinion scenario, whereas its impact varied by user attributes in the assistant and expert scenarios. In addition, older users were more influenced by tone, and highly extroverted users exhibited discrepancies between their perceptions and decisions. Furthermore, open-ended questionnaires highlighted that users expect tone adjustments to enhance their experience while emphasizing the importance of tone consistency and ethical considerations. Our findings provide crucial insights into the design of explanation expressions.
Crisis maps are regarded as crucial tools in crisis communication, as demonstrated during the COVID-19 pandemic and climate change crises. However, there is limited understanding of how public audiences engage with these maps and extract essential information. Our study investigates the sensemaking of young, digitally native viewers as they interact with crisis maps. We integrate frameworks from the learning sciences and human-data interaction to explore sensemaking through two empirical studies: a thematic analysis of online comments from a New York Times series on graph comprehension, and interviews with 18 participants from German-speaking regions. Our analysis categorizes sensemaking activities into established clusters: inspecting, engaging with content, and placing, and introduces responding personally to capture the affective dimension. We identify friction points connected to these clusters, including struggles with color concepts, responses to missing context, lack of personal connection, and distrust, offering insights for improving crisis communication to public audiences.