Open University of the Netherlands Research Portal
Not a member yet
37139 research outputs found
Sort by
Understanding the Role of Clinical Decision Support Systems Among Hospital Nurses Using the FITT (Fit Between Individuals, Tasks, and Technology) Framework:Qualitative Study
No full textUnderstanding enterprise architecture management in the context of today's dynamic and digital world
No full textArtificial intelligence in customer service interactions: From multi-layered information to organizational insights
No full textServices shape our daily lives, from ordering coffee and streaming our favorite TV show to navigating technical issues and accessing healthcare. These customer service interactions generate vast amounts of information every day. However, organizations struggle to systematically analyze and learn from these interactions due to their volume and complexity. This dissertation examines how artificial intelligence (AI) can automatically extract meaningful patterns and insights from customer service interactions, transforming them into actionable information for organizations. Central to this approach is the recognition that service interactions contain multiple layers of information: explicit content (what is actually said), implicit signals (emotions, dissatisfaction, and call quality), and broader interaction-level patterns. Each signal requires specialized analytical techniques to unlock its value.The dissertation contains six interconnected studies, starting with a systematic literature review that establishes how technology can augment human service agents. From a customer-centric perspective, a comparative analysis of neural network approaches for speech emotion recognition shows that simpler models perform as well as more complex ones, while being more efficient to deploy. Building on this audio-based foundation, subsequent research investigates customer dissatisfaction detection from both text and audio, demonstrating that multimodal approaches significantly outperform single-channel methods. Shifting to a service agent-focused perspective, AI can automatically identify different response strategies that companies use in social media service interactions, with custom-trained models outperforming general-purpose pretrained models. The research then explores how computational approaches can assist human evaluators in call quality monitoring while highlighting the continued importance of human judgment. Finally, a curiosity-driven approach for aggregated knowledge extraction demonstrates how AI can dynamically structure collections of service-related documents into ontologies.Based on these chapters, this dissertation offers several key insights. First, service interactions contain various layers of information that can be extracted automatically. When aggregated across interactions, this information enables organizations to move from reactive problem-solving for individual interactions to developing strategic insights over multiple interactions. Second, the optimal AI approach varies depending on the specific task and context. The results show that simpler, domain-specific models often outperform complex, general, or pretrained models. Third, the findings suggest that the most effective applications emerge when AI technologies are combined with human expertise, rather than replacing human judgment. This dissertation establishes customer service interactions as underutilized sources of competitive advantage. It demonstrates that AI can systematically extract value across multiple information layers of service interactions. Rather than automating service delivery, these findings suggest that AI systems can provide analytical support that enhances human understanding of service interactions while preserving the essential human elements of customer service. The studies offer both a theoretical understanding of how AI can process interaction data and practical guidance for organizations that are seeking to implement these technologies effectively, contributing to knowledge at the multidisciplinary intersection of service management, information systems, and artificial intelligence research
Kunstmatige intelligentie aan tafel:Helpt AI voedingswetenschap vooruit?
No full textKunstmatige intelligentie (Artificial Intelligence, AI) klinkt niet langer als iets uit een sciencefictionboek. Veel mensen kennen ChatGPT, Gemini of andere AI-modellen. Er verschijnen regelmatig nieuwsberichten over mogelijke toepassingen van AI. Zo lijkt AI steeds vaker met succes te worden toegepast in de medische zorg. Bijvoorbeeld in diagnostiek of bij het ontwikkelen van nieuwe behandelmethodes voor aandoeningen die vroeger ongeneeslijk leken. Ook binnen de voedingswetenschap lijkt de belangstelling voor AI te groeien. Maar wat betekent dat precies voor voedingswetenschappers, diëtisten en iedereen met interesse in gezonde voeding? In dit artikel worden recente wetenschappelijke reviews (vooral eerste helft 2025) besproken over AI-trends in de voedingswetenschap
The PET@home Toolkit When the pet’s carer receives long-term care at the family home
Full text linkThrough this project, we have gained insight into the significance and roles of pets for clients receiving long-term care at home and developed the PET@home Toolkit to support professional caregivers, family caregivers, and clients living with pets. The toolkit aligns with the person-centred care paradigm and requires minimal effort and training for professional caregivers. It was developed to help users address the benefits and challenges associated with pet ownership in long-term care at home settings, and to promote responsible and lasting relationships between clients and their pets, benefiting all parties involved.The Dutch versions of the PET@home Toolkit, its implementation plan, and e-learning module are accessible at no cost through the University Knowledge network for Older adult care Nijmegen (www.ukonnetwerk.nl) and the Open Science Framework (https://doi.org/mxh2
Voorspellende factoren voor behandeling bij een bekkenfysiotherapeut
No full textVeel vrouwen met bekkenbodemklachten ervaren seksuele problemen en psychologische distress. De problemen die ervaren worden, kunnen gerelateerd zijn aan zwangerschappen en bevallingen. Niet alle vrouwen met bekkenbodemklachten zijn echter onder behandeling bij een bekkenfysiotherapeut. Hun besluit om behandeling aan te gaan kan het resultaat zijn van expliciete en impliciete cognitieve processen. Daarom is onderzocht of zwangerschap, bevalling, ernst van de bekkenbodemklachten, seksuele problemen, psychologische distress en de impliciete associatie tussen hulp zoeken en seksuele problemen voorspellend zijn voor het in behandeling zijn bij een bekkenfysiotherapeut. Daartoe werden vrouwen uitgenodigd om een online enquête in te vullen en een online impliciete associatietest te doen. Psychologische distress bleek een belangrijke en sterke voorspeller te zijn voor het in behandeling zijn. Zwangerschap, bevalling, de ernst van de bekkenbodemklachten en positieve impliciete associaties tussen hulp zoeken en seksuele problemen voorspelden ook dat vrouwen in behandeling waren. Seksueel functioneren was niet voorspellend. Om de complexe rol van seksueel functioneren in de context van behandeling te ontrafelen is meer onderzoek nodig. Meer kennis kan de zorg voor vrouwen met bekkenbodemklachten en seksuele problemen verder verbeteren
Reassessing the diversity and distribution of African rope squirrels (Funisciurus Trouessart, 1880)
No full textThe diversity, taxonomy, distribution and ecology of sub-Saharan tree squirrels remain under-researched. This study aims to elucidate the diversity and distribution of rope squirrels, genus Funisciurus Trouessart 1880, in the Congo Basin. We assembled the most comprehensive genetic and morphometric data set to date, on a significant portion of the geographical and taxonomic range of these squirrels (470 specimens from seven provinces of the Democratic Republic of Congo). We identified six main taxa: a previously undescribed Funisciurus species (here, Fx), three allopatric taxa of Funisciurus anerythrus (Fc, FaRB and FaLB), and two sympatric genetically distinct taxa (FbLB1, FbLB2), potentially belonging to a Funisciurus bayonii species complex. We then mapped their distribution, showing that the Congo and Kasaï Rivers represent significant biogeographical barriers limiting the distribution of Funisciurus species. In addition to providing a baseline for research on the impact of climate change and habitat degradation on the abundance and distribution of rope squirrels, our findings support research on the role of rope squirrel species in the transmission of pathogens of public health importance.Teaser text We studied the diversity and distribution of rope squirrels, genus Funisciurus Trouessart 1880, in the Congo Basin. By gathering the most comprehensive genetic and morphometric data to date on a significant part of the geographical and taxonomic range of these squirrels (specimens from seven provinces of the Democratic Republic of Congo), we identified six main taxa: one previously undescribed species, three allopatric taxa, and two genetically distinct sympatric taxa. We then mapped their distribution, showing that the Congo and Kasai rivers represent significant biogeographical barriers limiting the distribution of Funisciurus species. These results support research into the role of rope squirrel species in the transmission of pathogens of public health importance
Speckle Tracking Echocardiography in Twin Pregnancies and the Role of Global Longitudinal Strain and Peak Systolic Strain:A Systematic Review and Meta-Analysis
No full textIntroduction: Twin pregnancies are associated with an increased risk of perinatal morbidity and mortality. Pregnancy complications related to twins, such as fetal growth restriction, and twin-to-twin transfusion syndrome (TTTS), are associated with hemodynamic changes in the fetal heart. Two-dimensional speckle tracking echocardiography (2D STE) is a tool to evaluate fetal cardiac function. This paper aims to review the literature regarding global longitudinal strain (rate) and peak systolic strain (rate) assessed with 2D STE in twin pregnancies. Feasibility, frame rate, and angle of the fetal heart at the time of measurement were selected as secondary outcomes. Methods: The databases Medline, Embase, Scopus, and Web of Science were searched. Results: Seven articles met the inclusion criteria and selected all monochorionic diamniotic (MCDA) twins with TTTS as the study population. The global longitudinal strain in the right and left ventricle and the peak systolic strain in the right ventricle of the recipient MCDA twin are significantly decreased compared to the donor MCDA twin. 2D STE assessment was shown feasible and reproducible in MCDA pregnancies. Large heterogeneity in technical characteristics between the articles induces inconsistent results. Conclusion: Although feasible, the knowledge of 2D STE is very limited in twin pregnancy. Prospective studies are needed to evaluate the 2D STE assessment in uncomplicated twin pregnancies considering its possible additive value in the diagnostics of pregnancy-related pathologies.</p
Constructing collective learning
No full textProfessional Learning Communities (PLCs) in education are intended to promote both individual and collective learning; however, collective learning does not always materialize. This study aimed to deepen our understanding of the processes that shape collective learning, by focusing on a cognitive perspective on collective learning thus complementing the more commonly used social perspective on collective learning in PLCs. This cognitive perspective consisted of collective learning as the interplay between the psychological mechanisms of self-categorization, collective attention, common knowledge, and collective identity. Using a qualitative case study approach, that involved interviewing all eleven members of two newly formed multidisciplinary PLCs, experiences with constructing collective learning were collected. A combinatory inductive and deductive analysis was performed, which confirmed the foundational mechanisms of collective learning as defined by the cognitive perspective. In addition, a fifth mechanism, social equivalence, was distinguished, which offers further insight into the interaction between self-categorization and collective attention during the early stages of PLC functioning. Social equivalence refers to the process through which members of PLCs attribute constructed similarities—such as shared values and norms—to their peers at an abstract level. These similarities not necessarily have a basis in reality, but they serve to foster connectivity, facilitating collective learning relationships with unfamiliar individuals.</p
A comparison of valuation methods for cultural ecosystem services in support of ecosystem accounting
No full textAssigning an economic value to cultural ecosystem services is important to promote their sustainable and rational use. Valuation of such services requires a non-market approach as they are not traded on markets and, thus, have no directly observable market price. The System of Environmental-Economic Accounting – Ecosystem Accounting (SEEA-EA) aims to develop a systematic approach to value ecosystem services aligned with the valuation approach of the national accounts. However, valuing cultural services in SEEA-EA is challenging and different approaches have been developed. In this study, we compare four prominent approaches for valuing cultural ecosystem services: resource rent, travel cost method, simulated exchange value and consumer expenditure. We test and compare these methods in a case study of Ugam Chatkal State Nature National Park in Uzbekistan and examine to what degree the methods are aligned with accounting valuation principles. We note that the methods assess value in a different way and, accordingly, we find considerable differences amongst approaches in recreational value: values ranged between US65.19M annually. The lowest value was provided by the resource rent approach and the highest value by the travel cost method including consumer surplus. This latter method is not aligned with SEEA-EA accounting; however, even the three methods that are aligned with accounting principles provide quite different value estimates. The two other approaches, simulated exchange value and consumer expenditure, provided an annual value of US13.5M, respectively. We find that a resource rent method is likely to underestimate the 'true' value of the service when used for accounting and that the simulated exchange value method seems to be best aligned with the valuation needs for cultural services for SEEA-EA.</p