67471 research outputs found
Sort by
Gamification Research for Autistic People: A Scientometric Analysis and Scoping Review
Get PDFGamification for autistic people is an emerging area of research. However, the existing literature, developed over just a little more than a decade, remains insufficiently mapped and understood by the academic community. To address this gap, we conducted a scientometric analysis combined with a scoping review. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework to conduct the study. Key themes, types of interventions, and publication venues were identified, along with trends in publication activity, major contributors, and prevailing methodological designs. The findings highlight the need for future international and interdisciplinary collaborations, the conduct of longitudinal studies, and a stronger emphasis on knowledge translation and practical impact. Our study contributes to the fields of mental health and gamification by tracing the evolution of gamification research for autistic people over time and by offering insights to guide future developments in the field
Designing Algorithmic Ensembles for Fair and Accurate AI-based Mammography Screening
Get PDFAs AI algorithms become increasingly prevalent in healthcare, ensuring both accuracy and fairness in decision-making poses a dual challenge. Breast cancer screening is a particularly high-stakes example: FDA-cleared AI tools are already in clinical use, and nearly 40 million mammograms are performed annually in the United States, yet many of these systems have been trained on limited subpopulations, raising equity concerns. We address this challenge by leveraging the diversity of predictive algorithms developed for the same task and forming a linear ensemble. We develop a statistical model that establishes conditions under which such an ensemble can satisfy equal-opportunity fairness and then demonstrate its application using simulated data calibrated from a real-world AI mammography competition. Our analysis shows that ensembles can improve both accuracy and fairness, especially when constituent algorithms differ in subgroup performance. These findings provide actionable guidance for health
Affective Foraging: Knowledge Graph-Assisted Analysis of Emotion and Topic Information Patches in Online Discourse on the 2025 US Tariffs
Get PDFThe tariffs introduced by the second Trump administration in early 2025 sparked significant public discourse on social media. This paper presents a computational framework for analyzing the emotional and thematic content of this discourse, focusing on YouTube as a key platform. We introduce a novel methodology for emotion detection and topic modelling using a combination of GenAI and embedding-based models to analyse 5874 transcripts and 866673 comments. The knowledge graph created from this data revealed clusters of related emotions and topics which were subsequently used to surface patterns of affective foraging. These patterns highlight the ways in which users navigate emotional content and seek information in a complex digital landscape. Our results contribute to the field of Information Systems by adding an emotional dimension to Information Foraging Theory, proposing the concept of Affective Foraging that integrates Digital Emotion Regulation with the latter to depict “informavores” as emotionally inclined, irrational decision-makers
Sweet Talks: An Initial Design Science Research Approach to Enhance Trust in Conversational Agents for Diabetes Self-Management
Get PDFConversational Agents (CAs) are a promising solution to support people with chronic diseases in the self-management of their condition. Diabetes patients, who have to perform various complex and demanding self-management activities on a daily basis, can especially benefit from this technology. However, a lack of trust in CAs hinders their acceptance and adoption. Despite its high importance, systematically derived design knowledge regarding trust in CAs is scarce. This research paper aims to pro-vide a first step toward a design theory for enhancing the trustworthiness in CAs. A design science research approach is followed to identify design requirements and derive design principles based on expert interviews with diabetes patients and a literature analysis. The findings of this research paper help to enhance the trustworthiness of CAs to increase their acceptance and adoption, thereby contributing to greater engagement in self-management activities
Understanding Human and AI Complementarity: Perspective of FGCS Employees
Get PDFLeveraging human and artificial intelligence (AI) benefits work performance but our knowledge about effective human-AI collaboration remains limited. The study examines the employment experiences of first-generation college students (FGCSs) and their perceptions of human-AI labor division at their workplace. Data were collected from a survey of FGCS employees who attended a public, four-year university in the United States in 2025. Guided by the sociotechnical systems theory and task-technology fit with AI literature, we conducted a thematic analysis on the narrative data of the employees. The qualitative analysis revealed four major themes including AI augmentation, AI automation, human capabilities, and the negative view of “AI Is Not Needed.” The findings suggest that FGCS employees face several challenges, including the lack of knowledge about AI capabilities and ignorance of AI integration at work. The study contributes to the AI and work literature and offers practical implications and suggestions for future research
The BI Trap – A Tripping Risk on the Way to the Successful Use of Process Mining
Get PDFProcess mining (PM) is one recent technology trend with considerable potential for process optimization. We have noticed that the PM application in literature seems to be further along than the actual implementation in practice. In theory, the optimal process mining application encompasses the entire spectrum, from process discovery to action-oriented process mining. In practice, however, full utilization is rarely observed. To investigate this further, we conducted a qualitative study and interviewed 27 users in various positions from 16 different companies. We found that companies often stagnate in the early stages of application development and are therefore unable to generate sustainable value with PM. Actual process optimizations are carried out manually or not implemented at all. Based on this, we conceptualize the “BI trap” that companies may fall into when implementing and using PM, and have developed recommendations to avoid this scenario and ensure the successful and full utilization of PM
If You Move to Our Country, Learn the Language! A Netnography Approach to Studying Language Ideologies in Finland
Get PDFIncreasing migration can be perceived as both a valued necessity and a threat to national values and norms. These oppositional views can be reflected in societal language ideologies, i.e. shared sets of beliefs about language(s) amongst particular social groups. Especially in non-Anglophone countries where the influx of migrants is marked by an uptake in the use of English as a common language, language ideologies may become polarized and nationalistic. In this study, we take a netnography approach to study language ideologies in the national context of Finland. By engaging in immersion across several online communities – including online comment sections of Finland’s largest broadsheet newspaper (Helsingin Sanomat), Discord, and Facebook – we detail how the affordances of digital technologies evoke and exacerbate language-based groupings, contributing to the polarization of language ideologies. In doing so, this study extends research on language ideologies and the role of ICT in socio-cultural polarization
Human-in-the-loop Hybrid and Automated Pre-processing for Zero-shot Aerial Part-matching via Analogical Reasoning
Get PDFAccurate and efficient object identification under occluded imagery conditions remains a core challenge in common machine learning tasks such as image recognition and autonomous vehicle navigation. We introduce the Part-annotated Fine-Grained Visual Classification of Aircraft (“Part-annotated FGVC-A”) dataset consisting of over 2,700 images with labels for four to nine pre-identified airplane parts. We use the visual probabilistic analogy mapping (visiPAM) model to demonstrate two complementary data pre-processing pipelines for zero-shot part matching between different aircraft. First, a human-in-the-loop procedure achieves 64% accuracy but requires 204 hours of manual annotation. Then, we automate this pipeline using semantic segmentation and clustering, resulting in a 76.9% accuracy, 22% higher than the human-in-the-loop approach, while cutting pre-processing time by 97%. These results demonstrate the potential of analogical reasoning as a zero-shot solution for part-based identification tasks for various computer vision applications dealing with minimally-labeled or occluded data
Cognitive Power for Management Through Reasoning Support
Get PDFIISR methodologies are roadmaps for infor-mation systems research that are adapted to cho-sen contexts and state-of-the-art theory to develop IS support that can give best possible guidance for (often consequential) managerial decisions. The paper works out guidance for efficient, effective or explicable management decisions. The general principles and the development history – from the early days of Operational Research and Management Science to digital ecosystem platforms for management – show how requirements on ISR methodology have evolved. An ISR methodology for the 2030’es will still rest on the decision analysis tradition to support efficient and effective managerial decisions in relevant problem-solving contexts. The flexibility and ideology of decision support systems will prevail to show how operating managers can boost performance with IS instruments, tools and technology. Digital ecosystem platforms that support the use of reasoning artificial intelligence will continue, expand and improve on the DSS ideology