NIMS: MagIC - Artigos em revista internacional com arbitragem científica (Peer-Review articles in international journals)
URI permanente para esta coleção:
Navegar
Entradas recentes
- Towards circular economyPublication . Simões, João; Neves, Catarina; Oliveira, Tiago; Azadi, Hossein; Goli, Imaneh; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management School; ElsevierThe transition to a circular economy presents an imperative need regarding the unsustainable consumption patterns and growing environmental degradation. Indeed, the circular economy is being presented as a sustainable solution, wherein materials are reused, recycled and regenerated to optimize the use of resources. Therefore, this study explores how digital product passports can empower citizens to actively engage in environmentally responsible consumption. Despite the recognition of citizens as essential drivers of circular economy efforts, their role in adopting sustainable technologies remains underexplored. This study aims to identify the motivational and behavioral factors that shape citizens’ willingness to use digital product passports, bridging gaps in current knowledge about individual engagement with circular economy technologies. Therefore, a research model was built and tested using structural equation modeling. The findings expose the factors that significantly influence consumers’ intention to use digital product passports, namely trust, desire to have more information on the product, ad pro-environmental attitude, this last with a strong moderating impact on the proposed relationships. Based on this, the study contributes to the broader understanding of sustainable innovation and its societal impacts, advancing circular economy strategies, such as the use of DPPs.
- Lower body parkinsonismPublication . Jalles, Constança; Simões, Rita M.; Sakallioglu, Berfin; Vanneschi, Leonardo; Ferreira, Joaquim J.; Reimão, Sofia; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management School; ElsevierBackground Magnetic resonance imaging (MRI) planimetric biomarkers such as the midbrain to pons (M/P) ratio, magnetic resonance parkinsonism index (MRPI), and MRPI 2.0 have demonstrated high diagnostic accuracy discriminating Progressive Supranuclear Palsy (PSP) patients from other atypical parkinsonisms and Parkinson’s Disease (PD). However, these indexes have not been studied in the specific context of lower body parkinsonism (LBP), where the differential diagnosis between PSP, vascular parkinsonism (VP) and normal pressure hydrocephalus (NPH) is of great clinical relevance. Objectives Our aim was to study MRI planimetry in LBP patients, assessing its role in the differential diagnosis. Methods We analyzed MRI planimetric measures, ratios and parkinsonism indexes in a retrospective sample of 71 subjects with an established clinical diagnosis: 23 of VP, 12 of NPH, 23 of PSP, compared with a group of 13 PD patients without gait or postural changes. Results All groups with LBP-associated diagnosis showed smaller midbrain areas and wider third ventricle and frontal horns widths than the PD group. The PSP group presented the highest medians of P/M ratio, MRPI and MRPI 2.0, significantly different from all groups except NPH. The MRPI 2.0 discriminates PSP and NPH from VP patients at group level. Conclusions Our study found that MRPI 2.0 is able to differentiate PSP and NPH from VP at group level contributing to the differential diagnosis of LBP. Additionally, midbrain size reduction, and third ventricle and frontal horns enlargement may constitute key imaging features of LBP phenotype, including VP, NPH and PSP patients, differing from PD.
- Moderated mediation with compositesPublication . Schamberger, Tamara; Schuberth, Florian; Henseler, Jörg; Information Management Research Center (MagIC) - NOVA Information Management School; SpringerModerated mediation models are crucial in many disciplines, particularly the social sciences. Researchers use them to analyze the conditions under which different variables are related. Structural equation modeling (SEM) is an eminently suitable framework for this endeavor. In fact, several approaches have been proposed and extended to model moderated mediation effects involving reflectively measured latent variables. However, approaches to modeling moderated mediation involving unknown-weight composites (i.e., weighted linear combinations of variables whose weights are estimated freely) are limited in either model specification or model assessment. Unknown-weight composites are used, for example, to model formative constructs or collections of heterogeneous causes. In this study, we propose composite moderated structural equations (CMS), a new approach that combines latent moderated structural equations (LMS), the standard SEM approach for estimating moderation effects among latent variables, with the H–O specification, a recently introduced specification for flexibly modeling composites. A Monte Carlo simulation demonstrates the performance of CMS and confirms that CMS enables researchers to flexibly model and estimate moderated mediation effects involving unknown-weight composites.
- How AI-Driven Chatbots Shape Customer Satisfaction and Loyalty to Chatbot Usage in Digital Service ExperiencePublication . Rita, Paulo; Vong, Celeste; Correia, Catarina; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); Elsevier Science Publisher B.V.This research investigates the impact of AI-driven chatbots on customer satisfaction, loyalty to chatbot usage, and purchasing intentions in digital service environments. While chatbots enhance efficiency and provide 24/7 availability, their ability to meet consumer expectations and drive engagement remains a topic of debate. Drawing on a survey of 282 respondents and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM), this study identifies the chatbot attributes that drive customer satisfaction. The results reveal that information quality, problem-solving capability, and understanding of humanness significantly enhance satisfaction. In contrast, perceived contingency, response humanness, and anthropomorphic cues have no impact on satisfaction, underscoring the importance of designing chatbots that excel in providing accurate information and resolving customer issues efficiently. These insights contribute to a deeper understanding of how AI technologies can be leveraged to meet consumers' evolving needs in digital environments.
- Interpretable machine-learning diagnosis of forest gross primary productivity patterns in China’s protected areasPublication . Cabral, Pedro; Ren, Xiaofeng; Zhu, Chenxia; Yeboah, Emmanuel; Wang, Guojie; Xu, Erwen; Jing, Wenmao; Charrua, Alberto; Hakam, Oualid; Costa, Ana Cristina; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); Elsevier BVUnderstanding the spatial variability of forest gross primary productivity (GPP) is essential for diagnosing ecosystem functioning and supporting monitoring and management within protected areas. However, many data-driven approaches emphasize predictive performance while offering limited interpretability of the drivers underlying spatial heterogeneity. Here, we develop an interpretable machine-learning framework to diagnose spatial patterns and dominant drivers of forest GPP within China’s national-level protected areas. Satellite-derived GPP and environmental variables were aggregated to a 0.1° spatial grid over 1990–2018 to characterize long-term mean forest productivity. Multiple machine-learning models were evaluated, and the best-performing model was interpreted using explainable artificial intelligence to quantify driver importance and response behavior. The mean forest GPP was 759.5 g C m⁻2 yr⁻1, with pronounced spatial heterogeneity. Approximately 22% of protected areas experienced increases in forest GPP exceeding 20% between 1990 and 2018, primarily in humid regions, whereas 12.5% showed declines greater than 20%, mainly in the southern Qinghai-Tibet Plateau, northern arid regions, and west-central temperate semihumid zones. Among the evaluated models, XGBoost achieved the highest predictive performance on independent test data (R2 = 0.76, RMSE = 262 g C m⁻2 yr⁻1). Precipitation, temperature, and solar radiation emerged as the dominant drivers, with precipitation explaining 53.4% of the study area, followed by temperature (19.7%) and solar radiation (16.0%). Forest fragmentation exhibited a predominantly negative association with forest GPP. This study is a spatial diagnostic analysis that provides transparent insights to support spatial prioritization, monitoring design, and management planning within protected areas.
- Exploring Users’ Acceptance and Engagement with Mental Health ChatbotsPublication . Yang, Yanrong; Oliveira, Tiago; Tavares, Jorge; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); John Wiley & Sons, Ltd.Background The potential of well-being chatbots as supportive tools in mental healthcare is increasingly recognised. Nevertheless, user acceptance remains low, highlighting the need to understand the factors influencing adoption and engagement. Objective: The purpose of this study is to identify the factors influencing user acceptance and engagement with chatbots and to generate insights that can inform the design and implementation of more effective chatbot interventions for mental well-being. Methods: Following the PRISMA 2020 guidelines, an integrative review was conducted in June 2024. Literature searches were carried out in Web of Science, Scopus, PubMed, IEEE Xplore and ScienceDirect to identify peer-reviewed articles published between January 2010 and May 2024. Thematic analysis was employed using an inductive approach. Results: From a total of 1232 papers identified, 20 studies met the inclusion criteria. The findings developed three themes, which involve technological factor, user factor and environmental factor. Different subtopics within the technological aspects have different effects on user behaviour. Technological limitations and excessive anthropomorphism have emerged as key barriers to user–chatbot interaction; empathy, interactivity, user-centred design, ease of use, personalisation, usability and stability were found to promote user engagement. From the user perspective, barriers included lack of motivation, low trust, privacy concerns and effort expectations, while facilitators encompassed enjoyment, positive attitudes, learning opportunities and emotion. Environmental factors could influence user adoption behaviour, for instance, advertising and social influences. Conclusions: Multiple interdisciplinary factors have been found to influence user engagement with chatbots for mental well-being. This will contribute to refining extant theories and fostering interdisciplinary collaboration. Moreover, this study provides a valuable source of instruction for designers and developers of health chatbots.
- SBBrasil TrainSheetsPublication . de Campos Souza, Paulo Vitor; Batista, Huoston Rodrigues; Silva, Alisson Marques da; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); Institute of Electrical and Electronics Engineers (IEEE)Oral health is increasingly recognized as a public priority due to its strong association with overall well-being. However, both evaluator training and computational model development are constrained by the scarcity of publicly available, context-rich dental image datasets. This study presents a reproducible data-engineering pipeline, named SBBrasil TrainSheets, that transforms public PDF manuals from national oral health programs into structured, analyzable image corpora suitable for translational research. The proposed system automates image extraction, organizes volunteer-captured anatomical views, and embeds features for unsupervised quality control. A human-in-the-loop labeling interface prioritizes uncertain samples to improve annotation efficiency. As a proof-of-concept, a lightweight baseline classifier was trained to distinguish dental views (frontal vs. occlusal) using a volunteer-level split, achieving 96.4% accuracy after a short calibration phase. Overall, the pipeline enables reproducible dataset construction from existing public materials and supports quality assurance, educational applications, and downstream computational analysis in dental public health.
- A Daily Soil Moisture–Temperature Compound Index for Characterising Dry–Hot ExtremesPublication . Aftab, Rukhshinda; Wang, Guojie; Hagan, Daniel Fiifi Tawia; Shan, Baoying; Siddique, Fareeha; Zhou, Chensi; Yeboah, Emmanuel; Cabral, Pedro; Information Management Research Center (MagIC) - NOVA Information Management School; Royal Meteorological SocietyCompound dry–hot extremes are increasing globally, yet existing indices often overlook the critical role of soil moisture in regulating moisture surplus or deficit. This study proposes the Standardised Soil Moisture Temperature Compound Index (SSTCI), a globally applicable, daily-scale index derived from the joint probability of the Standardised Antecedent Soil Moisture Index (SASMI) and Standardised Temperature Index (STI). To improve event classification, SSTCI incorporates an objective removal and merging procedure that filters minor spells and consolidates temporally dependent events. As a case study, we apply SSTCI to the Poyang Lake Basin (1961–2020), where it performs better than existing indices in detecting CDHEs, validated by recorded events. Spatiotemporal analyses show a significant rise in event frequency and intensity over recent decades. By integrating soil moisture dynamics and operating at a sub-monthly scale, SSTCI enhances the accuracy of CDHE monitoring, offering a robust tool for early warning and risk assessment.
- Joint probabilistic modeling of cement strengthPublication . Islam, Mazharul; Li, Changjiao; Yang, Bo; Liu, Cong; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management School; ElsevierIn cement manufacturing, ensuring simultaneous compliance with compressive (CCS) and flexural strength (FS) requirements is challenging due to their divergent responses to shared inputs. Industrial variability (e.g., fluctuations in C3S content, grinding heterogeneity, and curing conditions) exacerbates this challenge, leading to high batch rejection (15–20%) and excessive clinker overdesign that contributes 7% of global CO2 emissions. Traditional single-property models fail by treating CCS and FS in isolation, producing deterministic predictions that ignore uncertainty, and conflating material-driven (aleatoric) with model-induced (epistemic) uncertainty—precluding risk-aware decisions. To overcome these limitations, this study introduces the Multi-Property Cement Strength Estimator (MPCSE)—the first joint probabilistic framework to model CCS and FS as full distributions via multi-head Gaussian Mixture Models with shared latent representations. MPCSE delivers four innovations: (1) joint probabilistic modeling that captures cross-property dependencies (7.8% lower MAE for CCS and 9.3% for FS versus single-property baselines); (2) explicit uncertainty decomposition enabling targeted process control (e.g., tighter grinding for 36–52 μm particles reduces FS variability by 15%) and strategic data collection (e.g., low-C3A regimes, < 4%); (3) a novel dual-strength compliance probability metric, P(CCS ≥ cmin ∩ FS ≥ fmin), revealing a near-total collapse to 0.38% at 50 MPa CCS / 9 MPa FS in industrial settings (versus 11.2% under controlled laboratory conditions) and quantifying the previously unmeasured risk of simultaneous failure; (4) context-dependent mechanistic interpretability via SHAP analysis, showing granulometry (uniformity index, SHAP = 0.032) dominates industrial variability while stoichiometry (C3S, SHAP = 0.058) governs laboratory performance—explaining the CCS–FS correlation gap (lab r = 0.945 vs. industry r = 0.101). MPCSE achieves > 95% confidence-interval coverage on industrial data and enables 12–15% clinker reduction with approximately 25% fewer batch rejections through risk-aware rerouting of borderline batches, advancing sustainable cement production.
- Understanding recreational vehicle user preferencesPublication . Ribeiro, João; Naranjo-Zolotov, Mijail; Acedo, Albert; Trilles, Sergio; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management School; Routledge Journals, Taylor & Francis LtdCaravanning has grown rapidly in popularity across the Iberian Peninsula, raising challenges for the planning and management of infrastructure tailored to recreational vehicles. Despite this growth, research on caravanning remains limited, particularly regarding user satisfaction and spatial infrastructure adequacy. In this study, more than 154,000 user reviews from the Park4Night platform were analysed, covering 1,581 recreational vehicle parking areas in Portugal and Spain. The objective was to identify user preferences and expectations across free, public paid, and private recreational vehicle areas in these countries. Text mining techniques, including topic modelling and N-gram analysis, were applied to identify the main aspects influencing user satisfaction, such as water and sanitation services, noise levels, pricing, and staff friendliness. Our findings reveal distinct patterns of user expectations based on parking area type, with free areas highlighting basic needs, while paid and private areas are subject to higher expectations related to amenities and service quality. Positive user feedback frequently emphasises quietness, accessibility, and cleanliness, while negative reviews often cite poor sanitation, noise, and inadequate services. The results inform targeted infrastructure improvements and policy recommendations for local governments and private operators.