67471 research outputs found
Sort by
Beyond Accuracy: Rethinking the Value of AI in Decision-Making Through Baseball’s Automated Ball-Strike (ABS) System
Get PDFThis paper examines how organisations integrate AI systems to support decision making by studying Major League Baseball’s multi-year experimentation with the Automated Ball-Strike (ABS) system – commonly known as ”robot umpires”. While automating the strike zone may appear to be a straightforward technical task, our study reveals that it entails complex practices of negotiation and meaning making over time. Rather than the simple adoption of a decision aid, the implementation of ABS became a site of organisational sensemaking. We argue for a need to move beyond user-centric models toward stakeholder-centric, contextually embedded frameworks for understanding AI in organisational decision-making
Reframing Transport Poverty through a Community-driven Design Approach
Get PDFThis study explores how a community-driven design approach can address human flourishing in the context of mobility. Drawing on design ethnography and co-design in two Swedish urban areas, the study surfaces alternative design ideas rooted in everyday life and community values. The research contributes to design for social sustainability by illustrating how place-based, participatory processes can make room for local narratives and values, offering a pathway for embedding wellbeing into the design process
Granular Spatio-Temporal Grid-based Machine Learning for Forced Outage Prediction in Electrical Networks
Get PDFWe developed a Granular Grid-based Outage Prediction Model, GG-OPM, that utilizes outage dependencies between electric grid substations and related feeders, benefiting from more granular weather data to improve outage prediction in the distribution network. The model incorporates a spatial and temporal module and tunes the hyperparameters to allow selecting components that optimize the task performance. Sixteen levels of spatio-temporal granularities were tested, using a large real-life dataset from a major Texas utility, which consisted of six years of historical outage events. The results obtained indicate an improvement of up to 50 times in F1 score over an earlier developed baseline for the most challenging prediction task, and an overall improvement across all levels of temporal and spatial granularity, providing solid grounds for utilizing the method in real-life outage prediction scenarios
Virtual Encounters, Real Impact? How Social Media Affordances Foster Intergroup Contact
Get PDFThis paper examines how social media affordances can facilitate positive intergroup contact to enhance social cohesion in democratic societies. Using social media affordance, we analyzed 30 empirical studies published between 2012 and 2025 that investigated intergroup contact through social media platforms. Our findings reveal that 27 studies documented improved intergroup attitudes across diverse contexts spanning ethnic, religious, and sexual orientation divisions. However, the analysis exposes significant untapped potential: while some affordances dominated the research, others received little attention despite their alignment with optimal contact conditions. We demonstrate social media’s capacity to transcend traditional barriers to intergroup encounter while revealing substantial opportunities for future platform design. This implies that thoughtfully leveraged social media affordances could enable scalable interventions for strengthening inclusion principles
Feasibility of a Wearable Remote Monitoring Device for Patients Treated for Opioid Use Disorder in a Telehealth Program
Get PDFOpioid use disorder (OUD) is increasingly prevalent in the United States. Telehealth-only OUD treatment with buprenorphine, first permitted during the COVID-19 pandemic, has expanded access but the modality complicates monitoring medication adherence and withdrawal symptoms. Remote patient monitoring (RPM) using smartwatch biometric sensors may improve telehealth OUD care, but feasibility is unknown. Patients (N=15) newly treated in a telehealth OUD program receiving buprenorphine were enrolled. Subjects were instructed to wear a smartwatch continuously, except during charging, for ten days. Adherence, defined as the proportion of hours in which at least one biometric data capture occurred, was measured. The mean adherence was 38.9%. Six patients (40.0%) demonstrated high adherence (>50%), and nine (60.0%) had low adherence. Although adherence was suboptimal, smartwatch-based RPM may be feasible in a telehealth-only OUD treatment program for some patients
Unlocking Ecosystem Potential: Balancing Supply and Demand in Open Government Data – A Systematic Literature Review
Get PDFOpen Government Data (OGD) initiatives aim to strengthen democratic structures through transparency and participation. However, early research focused heavily on benefits and supply, overlooking user needs and stakeholder dynamics, resulting in still low OGD usage. This study employs a systematic literature review to propose an integrative OGD ecosystem, identifying key influencing factors, interaction mechanisms, and value generation potential. Findings highlight that demand-side factors – personal, usage-related, and environmental – are central to OGD usage, while supply-side performance depends on resources, organizational, and environmental factors. Datasets form the baseline for usage, but social tools and features can significantly contribute to a functioning ecosystem. In addition to common benefit categories, our model introduces risks as a relevant but often neglected impact. Our holistic perspective reveals important interdependencies and promotes an integrated understanding of the OGD landscape
Designing Socially Grounded Data Pipelines for Training and Operating Socially Intelligent Robots: Challenges and Future Directions
Get PDFDesigning socially intelligent robots presents a frontier challenge in human–robot interaction and information systems research, where technical architectures must align with the embodied, context-rich demands of social life. Current Vision–Language–Action (VLA) models integrate multimodal inputs but fall short in supporting socially coherent behavior, limiting their value as training pipelines. Using a clinical problematization approach, this study examines experimental pipelines to identify structural limitations in temporal coherence, continuity, multimodal integration, and affective inference. These shortcomings reveal a deeper misalignment between prevailing training paradigms and the sociotechnical requirements of interactional integrity. In response, we highlight perception–language models (PLMs) as a more socially attuned substrate, capable of extracting contextual signals and enhancing situational grounding for behavior modeling. We conclude by outlining a research agenda that advances spatiotemporal reasoning, affective modeling, and embodied coherence, thereby contributing to IS discourse on the design of trustworthy, socially adaptive robotic systems
Beyond the Screen: Memory-Based Mechanisms and Personal Innovativeness in Voice Assistant Use
Get PDFThis study investigates how the mental retrieval of IT features influences innovative use behaviors with voice-activated devices (VADs). We conceptualize two memory-based constructs—IT feature recognition and IT feature recall—and examine their complex interplay. We theorize that their influence is moderated by users' personal innovativeness. Using a survey of 319 smart speaker owners, we found that both recognition and recall enhance innovative use, but their effects differ significantly based on an individual's disposition to innovate with IT. For users with high innovativeness, IT feature recognition drives innovation, while for those with low innovativeness, both recall and recognition contribute. These findings suggest that memory-based mechanisms are critical enablers of innovative use, highlighting the need for interfaces that support memory cues to foster broader feature utilization and innovative outcomes in voice-based interfaces
Designing for Imperceptible Interaction: Coordination Mechanisms in AI-Enabled Product-Service Systems
Get PDFImperceptible interaction, typically manifested in the completion of tasks with minimal user awareness of system mediation, constitutes the next frontier of human-computer interaction. Nevertheless, the convergence of artificial intelligence (AI) and product-service systems (PSS) that makes such interaction remains relatively underexplored. This study investigates how AI reconfigures PSS to realise imperceptible interaction. Drawing on a case study of Midea’s smart-home ecosystem from 2022 to 2024, and employing multi-source data analyzed through text mining and grounded theory, we develop a process model. The findings demonstrate that AI performs rule mapping, network activation, and logic learning, while PSS provides compatible control, flexible connectivity, and agile adaptation. The AI-PSS coupling generates three interaction mechanisms, including simplification, structuring, and subjectivation, that together transform explicit into imperceptible interaction and foster user co-creation. In doing so, the study contributes to advancing the theoretical understanding of how AI-enabled PSS supports the emergence of imperceptible interaction in human-computer interaction research
Corporate Ecosystem Start-Ups: An Organizational Approach for Successfully Scaling Data Ecosystems
Get PDFThe transition to cooperative, data-driven ecosystems is reshaping value creation in industries, driven by digital technologies. This paper examines the challenges and opportunities of scaling such ecosystems, focusing on a case study of a data-based solution for intralogistics developed by an industrial service provider in collaboration with ecosystem partners. The study highlights the limitations of established approaches in addressing joint governance, shared value creation, and trust essential for ecosystem success. To bridge this gap, the Corporate Ecosystem Start-Up (CESU) approach is proposed – a novel business innovation approach tailored to the unique demands of scaling solutions in data ecosystems. Drawing on insights from the practical case, the CESU approach is designed and evaluated using the criteria scope of action, risk and ownership, resources, and market access. Strategies to overcome organizational barriers and ensure alignment are described, providing a pathway to ecosystem growth. This research advances the understanding of scaling data ecosystems