In the shift towards human-centered manufacturing, our two-year longitudinal study investigates the real-world impact of deploying Cognitive Assistants (CAs) in factories. The CAs were designed to facilitate knowledge sharing among factory operators. Our investigation focused on smartphone-based voice assistants and LLM-powered chatbots, examining their usability and utility in a real-world factory setting. Based on the qualitative feedback we collected during the deployments of CAs at the factories, we conducted a thematic analysis to investigate the perceptions, challenges, and overall impact on workflow and knowledge sharing.
Our results indicate that while CAs have the potential to significantly improve efficiency through knowledge sharing and quicker resolution of production issues, they also introduce concerns around workplace surveillance, the types of knowledge that can be shared, and shortcomings compared to human-to-human knowledge sharing. Additionally, our findings stress the importance of addressing privacy, knowledge contribution burdens, and tensions between factory operators and their managers.@en

Digitally-supported participatory methods are often used in policy-making to develop inclusive policies by collecting and integrating citizen's opinions. However, these methods fail to capture the complexity and nuances in citizen's needs, i.e., citizens are generally unaware of other's needs, perspectives, and experiences. Consequently, policies developed with this underlying gap tend to overlook the alignment of multistakeholder perspectives, and design policies based on the optimization of high-level demographic features. In our contribution, we propose a method to enable citizens understand other's perspectives and calibrate their positions. First, we collected requirements and design principles to develop our approach by involving stakeholders and experts in policymaking in a series of workshops. Then, we conducted a crowdsourcing study with 420 participants to compare the effect of different text and images, on people's initial and final motivations and their willingness to change opinions. We observed that both influence participant's opinion change, however, the effect is more pronounced for textual modality. Finally, we discuss overarching implications of designing with empathy to mediate alignment of citizen's perspectives.@en

Domestic heating systems need to change to meet climate targets. We draw on practice theoretical concepts to understand what is needed to integrate heat pumps in Dutch households. From a design orientation, we view households as creative actors integrating technologies into daily life. We report on an ethnographic study of the disruptions and resulting reconfigurations that occur when heat pumps are introduced in Dutch households. Our findings reveal a variety of practice reconfigurations around heat pumps. We also find that these reconfigurations are related to and may influence other practices, including professional practices. We discuss our findings in relation to policy, technology development, and design, and conclude that the required reconfigurations in Dutch household practices could be supported, and that innovative practice reconfigurations emerging from internal household dynamics could contribute to sustainability transitions.

@en

Remote Patient Management systems (RPM) are crucial for addressing healthcare workforce shortages. These systems are often designed with a specified focus on clinical functionalities, without proper consideration for human-centric concerns. A care perspective is essential not only to acknowledge patients as people, but also to foster better quality of care and, ultimately, adoption. This highlights the gap of how RPM can embed caring. This work offers a systematic literature review aimed at developing "Caring RPM", a normative framework that integrates the philosophy of caring from nursing theory into RPMs. This framework underwrites the practical, moral, and relational aspects of patient care, including actionable recommendations to recalibrate RPM systems for more effective human-centric design. The framework can inspire new ways of embedding the caring dimension into HCI design practices.

@en

The exponentially growing digitisation of services that drive the transition from industry 4.0 to industry 5.0 has resulted in a rising materials demand for ICT hardware manufacturing. The environmental pressure, CO2 emissions (including
embodied energy) and delivery risks of our digital infrastructures are increasing. A solution is to transition from a linear to a circular economy (CE), through which materials that were previously disposed of as waste are re-entered back into product lifecycles through processes such as reuse, recycling, remanufacturing, repurposing. However, the adoption of the CE in the ICT sector is currently limited due to the lack of tools that support knowledge exchange between sustainability, ICT and technology experts in a standardised manner and the limited data availability, accessibility and interoperability needed to build such tools. Further, the already existing knowledge of the domain is fragmented into silos and the lack of a common terminology restricts its interoperability and usability. These also lead to transparency and responsibility issues along the supply chain. For many years now, the Semantic Web has been known to provide solutions to such issues in the form of ontologies and knowledge graphs. Several semantic models for the ICT, materials and CE domains have been build and successfully applied to solve complex problems such as predictive maintenance. However, there is a lack of a systematic analysis of the existing semantic models in these domains. Motivated by this, we present a literature survey of existing ontologies for ICT, materials and the CE, their possible applications, limitations and current CE standardisation efforts that can help guide its further implementation@en

Sustained adoption of automation is a problem for organizations, despite the promised benefits of automation and the propensity for organizations to expect it to transform their workplaces. To address this problem, previous work in HCI has mostly considered the perspectives and experiences of users interacting with automation technologies and has not considered the broader organizational context consisting of different stakeholders with varying needs and expectations around automation. Taking Amsterdam Airport Schiphol as a case study, we examine the challenges faced by practitioners responsible for integrating automation projects in its airside ecosystem, in an interview study conducted with 8 participants. Our findings reveal three challenges to the adoption of automation within the organization - the lack of consensus among different stakeholders, the need to adapt the technology to the specific context, and the undefined procedures required to maintain automation after implementation, that should be further addressed by the HCI community.@en

The study of urban greenspaces typically relies on three types of data: people’s subjective perceptions collected via questionnaires, vegetation indices derived from satellite imagery, such as the Normalized Difference Vegetation Index (NDVI), and Land Use or Land Cover maps, such as OpenStreetMap (OSM). Data on people’s perceptions are essential when researching human activities, yet they scale poorly. NDVI and OSM data, on the other hand, are freely available worldwide, thus valuable for assessing cities at scale or prioritizing locations for interventions. However, it is unclear how effectively NDVI and OSM data capture people’s visual perceptions of urban greenspaces. In this work, we collect people’s visual perceptions of public spaces in three major European cities through crowdsourcing, quantitatively compare them to NDVI and OSM data, and qualitatively investigate disparities. We found that NDVI moderately correlates with perceived greenness and that not only OSM greenspaces but also pocket parks and play spaces are often considered green. Furthermore, we found that people’s perceptions correspond best to OSM data in small radius distances and NDVI data in larger radius distances and that combining NDVI and OSM data can improve identification of places in OSM that are commonly considered green. Our qualitative analysis revealed that configuration and variety of vegetation, and presence of other natural or built-up features, influence people’s perceptions of greenspace. With our findings we aim to help researchers and practitioners make more informed decisions when collecting greenspace data for their specific context, ultimately contributing to green urban environments that reflect people’s perspectives.@en

Machine learning (ML) training data is often scattered across disparate collections of datasets, called <italic>data silos</italic>. This fragmentation poses a major challenge for data-intensive ML applications: integrating and transforming data residing in different sources demand a lot of manual work and computational resources. With data privacy constraints, data often cannot leave the premises of data silos; hence model training should proceed in a decentralized manner. In this work, we present a vision of bridging traditional data integration (DI) techniques with the requirements of modern machine learning systems. We explore the possibilities of utilizing metadata obtained from data integration processes for improving the effectiveness, efficiency, and privacy of ML models. Towards this direction, we analyze ML training and inference over data silos. Bringing data integration and machine learning together, we highlight new research opportunities from the aspects of systems, representations, factorized learning, and federated learning.

@en

The configuration of public open spaces plays a crucial role in shaping how different people use them. Nevertheless, our understanding of how the physical features of public open spaces influence the activities conducted within them, and the extent to which this impact differs across various individuals and population groups, is currently limited. In this study, we explore how the physical characteristics of public open spaces influence the likelihood of use among individuals, spanning different age and gender groups. By employing crowdsourcing, street-level imagery, statistical comparisons, and reflexive thematic analysis we uncover significant variations in the suitability of public open spaces for distinct activities, such as socializing or exercising. Greenspaces emerge as the preferred choice for almost all activities, whereas streets are consistently rated as the least suitable. Additionally, we identified various characteristics that influence the activities people are likely to engage in. These include the size of the space, the presence of seating, natural elements such as vegetation or water bodies, and the proximity to transport infrastructure. Surprisingly, we do not observe statistically significant differences in preferences among most age and gender groups. Overall, our study underscores the need for providing a diverse range of public open spaces tailored to accommodate different individuals, population groups, and activities.@en

Accessibility is a widely used concept across various disciplines to evaluate the degree to which individuals can reach desired destinations. Conventionally, accessibility is determined by the attractiveness of a destination and the associated travel cost to reach it. However, existing place-based accessibility measures do not differentiate between destinations accessible to individuals from a single demographic group and those accessible to individuals from diverse demographic groups. We propose a measure to assess the potential of distinct destinations to bring different individuals and demographic groups together, defining this property as co-accessibility. We demonstrate how measuring co-accessibility can enhance existing accessibility measures, describe its components, and provide a mathematical formulation for quantifying it. To illustrate the practical application of our measure, we conduct a case study in Amsterdam, the Netherlands, comparing the accessibility and co- accessibility of various destinations. This sample case study highlights the complexities and challenges inherent in measuring co-accessibility. Building on existing literature and our analysis results, we discuss the potential implications of co-accessibility, identify key challenges in its assessment, and recommend directions for future research.@en

Access to greenspace impacts children’s physical, social, and mental health. Numerous factors affect children’s access to urban greenspaces, often distinct from those affecting the general population, including parental restrictions, limited routine activity-space, and particular preferences. Most accessibility measures, however, employ the same principles for children and the general population, and a comprehensive exploration of factors and corresponding measures remains lacking. We conduct a scoping review and workshops with researchers and practitioners to identify factors affecting children’s access to greenspace, synthesize them into a conceptual model, and assess how existing accessibility measures address these factors. We focus on children aged 6–11 years old. Our analysis indicates children’s access involves a trade-off between reachability, determined by the route connecting the child’s starting setting to greenspace, and attractiveness, determined by how the greenspaces adhere to the child’s, and their companions’, preferences and motivations for visiting. Safety perceptions are important throughout. Existing accessibility measures predominantly emphasize reachability, neglecting personal characteristics and motivations. Based on our findings, we propose future directions for developing child-centered accessibility metrics. Our overview of metrics can facilitate decision-making in the selection of suitable measures, while our conceptual model can foster shared understanding of factors affecting children’s access to urban greenspace.@en

Pre-trained deep learning (DL) models are increasingly accessible in public repositories, i.e., model zoos. Given a new prediction task, finding the best model to fine-tune can be computationally intensive and costly, especially when the number of pre-trained models is large. Selecting the right pre-trained models is crucial, yet complicated by the diversity of models from various model families (like ResNet, Vit, Swin) and the hidden relationships between models and datasets. Existing methods, which utilize basic information from models and datasets to compute scores indicating model performance on target datasets, overlook the intrinsic relationships, limiting their effectiveness in model selection. In this study, we introduce TransferGraph, a novel framework that reformulates model selection as a graph learning problem. TransferGraph constructs a graph using extensive metadata extracted from models and datasets, while capturing their inherent relationships. Through comprehensive experiments across 16 real datasets, both images and texts, we demonstrate TransferGraph's effectiveness in capturing essential model-dataset relationships, yielding up to a 32% improvement in correlation between predicted performance and the actual fine-tuning results compared to the state-of-the-art methods.

@en

Web search has evolved into a platform people rely on for opinion formation on debated topics. Yet, pursuing this search intent can carry serious consequences for individuals and society and involves a high risk of biases. We argue that web search can and should empower users to form opinions responsibly and that the information retrieval community is uniquely positioned to lead interdisciplinary efforts to this end. Building on digital humanism---a perspective focused on shaping technology to align with human values and needs---and through an extensive interdisciplinary literature review, we identify challenges and research opportunities that focus on the searcher, search engine, and their complex interplay. We outline a research agenda that provides a foundation for research efforts toward addressing these challenges.@en

High-quality data plays a vital role in developing reliable image classification models. Despite that, what makes an image difficult to classify remains an unstudied topic. This paper provides a first-of-its-kind, model-agnostic characterization of image atypicality based on human understanding. We consider the setting of image classification "in the wild", where a large number of unlabeled images are accessible, and introduce a scalable and effective human computation approach for proactive identification and characterization of atypical images. Our approach consists of i) an image atypicality identification and characterization task that presents to the human worker both a local view of visually similar images and a global view of images from the class of interest and ii) an automatic image sampling method that selects a diverse set of atypical images based on both visual and semantic features. We demonstrate the effectiveness and cost-efficiency of our approach through controlled crowdsourcing experiments and provide a characterization of image atypicality based on human annotations of 10K images. We showcase the utility of the identified atypical images by testing state-of-the-art image classification services against such images and provide an in-depth comparative analysis of the alignment between human- and machine-perceived image atypicality. Our findings have important implications for developing and deploying reliable image classification systems.

@en

Recent research claims that information cues and system attributes of algorithmic decision-making processes affect decision subjects' fairness perceptions. However, little is still known about how these factors interact. This paper presents a user study (N = 267) investigating the individual and combined effects of explanations, human oversight, and contestability on informational and procedural fairness perceptions for high- and low-stakes decisions in a loan approval scenario. We find that explanations and contestability contribute to informational and procedural fairness perceptions, respectively, but we find no evidence for an effect of human oversight. Our results further show that both informational and procedural fairness perceptions contribute positively to overall fairness perceptions but we do not find an interaction effect between them. A qualitative analysis exposes tensions between information overload and understanding, human involvement and timely decision-making, and accounting for personal circumstances while maintaining procedural consistency. Our results have important design implications for algorithmic decision-making processes that meet decision subjects' standards of justice.

@en

Musical instrument recognition enables applications such as instrument-based music search and audio manipulation, which are highly sought-after processes in everyday music consumption and production. Despite continuous progresses, advances in automatic musical instrument recognition is hindered by the lack of large, diverse and publicly available annotated datasets. As studies have shown, there is potential to scale up music data annotation processes through crowdsourcing. However, it is still unclear the extent to which untrained crowdworkers can effectively detect when a musical instrument is active in an audio excerpt. In this study, we explore the performance of nonexperts on online crowdsourcing platforms, to detect temporal activity of instruments on audio extracts of selected genres. We study the factors that can affect their performance, while we also analyse user characteristics that could predict their performance. Our results bring further insights into the general crowd's capabilities to detect instruments.

@en

The proliferation of pre-trained ML models in public Web-based model zoos facilitates the engineering of ML pipelines to address complex inference queries over datasets and streams of unstructured content. Constructing optimal plan for a query is hard, especially when constraints (e.g. accuracy or execution time) must be taken into consideration, and the complexity of the inference query increases. To address this issue, we propose a method for optimizing ML inference queries that selects the most suitable ML models to use, as well as the order in which those models are executed. We formally define the constraint-based ML inference query optimization problem, formulate it as a Mixed Integer Programming (MIP) problem, and develop an optimizer that maximizes accuracy given constraints. This optimizer is capable of navigating a large search space to identify optimal query plans on various model zoos.@en

Emoji have become an essential part of modern communication, helping to convey emotions and tone quickly and concisely. Emoji used by humans and Intelligent Agents (IA) have been shown to affect people’s decision making intentions, suggesting they could be used to manipulate users to follow their advice. We present a mixed-methods crowdsourcing study (N = 194) that shows that adherence to an IA’s recommendation and user experience are not affected by emoji when used in a positive, collaborative way. However, we demonstrate that explanations provided by an IA do increase adherence to its recommendation.

@en

City streets that feel safe and attractive motivate active travel behaviour and promote people’s well-being. However, determining what makes a street safe and attractive is a challenging task because subjective qualities of the streetscape are difficult to quantify. Existing evidence typically focuses on how different street features influence perceived safety or attractiveness, but little is known about what influences both. To fill this knowledge gap, we developed a crowdsourcing tool and conducted a study with 403 participants, who were asked to virtually navigate city streets in Frankfurt, Germany, through a sequence of street-level images, rate locations based on perceived safety and attractiveness, and explain their ratings. Our results contribute new insights regarding the key similarities and differences between the factors influencing perceived safety and attractiveness. We show that the presence of human activity is strongly related to perceived safety, whereas attractiveness is influenced primarily by aesthetic qualities, as well as the number and type of amenities along a street. Moreover, we demonstrate that the presence of construction sites and underpasses has a disproportionately negative impact on perceived safety and attractiveness, outweighing the influence of any other features. We use the results to make evidence-informed recommendations for designing safer and more attractive streets that encourage active travel modes and promote well-being.@en