NIMS - Teses de Doutoramento (Doctoral Theses)
URI permanente para esta coleção:
Navegar
Entradas recentes
- Developing and Validating a Governance Measurement Scale for Ocean Ecosystem ServicesPublication . Andrade, Ronnie Joshé Figueiredo de; Cabral, Pedro da Costa BritoThis doctoral thesis develops and validates a decision-support scale for the governance of ocean ecosystem services, motivated by the practical need to make sustainable, collective decisions in complex marine contexts. Structured as three connected studies (presented as individual manuscripts), the research first maps how ecosystem services scholarship has evolved and where it is heading, then derives decision-relevant governance factors with expert input and finally tests whether these factors form a reliable and predictive measurement instrument for real-world use. The first study performs a bibliometric synthesis of ecosystem services review research over one decade, identifying dominant themes and future application directions, with particular emphasis on governance-oriented knowledge gaps. Building on this evidence base, the second study models a factor-development process for sustainable ocean ecosystem service decisions using the Delphi method with experts engaged in the NextOcean project (European Union Horizon 2020). This process results in a structured framework that organizes decision considerations into six dimensions, i.e., governance, people, planet, profit, cultural, and spatial, and explicitly links factors to stakeholder roles and to benefits, opportunities, costs, and risks. The third study experimentally validates the resulting scale through two-wave survey data collection from ecosystem-service stakeholders. Using exploratory factor analysis and internal consistency testing, the scale demonstrates strong reliability. Its explanatory and predictive capacity is then evaluated through classical linear regression and an artificial neural network, showing that the “planet”, “cultural”, and “profit” dimensions are the most influential in predicting governance decision outcomes. Overall, the thesis contributes an empirically grounded, operational tool to support adaptive governance by improving transparency, comparability, and efficiency in decision-making for ocean ecosystem services, while also outlining limitations and directions for broader cross-context testing.
- Artificial Intelligence for The Automatic Identification of Addresses: The Portuguese CasePublication . Cruz, Paula Isabel Moura Meireles; Vanneschi, Leonardo; Painho, Marco Octávio TrindadeAddresses can be used as quasi-identifiers to link relevant data across multiple registers, in a process known as address matching, essential to activities like urban planning, location-based services, and administrative census operations. On the other hand, address data quality has a direct impact on demographic and other spatial analyses, since it may lead to uncertainty and potential bias. This thesis aims at contributing to current knowledge in this field, using residential addresses managed by Statistics Portugal as a case study. We start by proposing a multiclass classification algorithm to evaluate the syntactic quality of residential addresses from a large database managed by Statistics Portugal, based on the NSGA-II algorithm and two modified kNN algorithms. The results show improved classification performance over baseline methods while simultaneously delivering insights on relevant features and local patterns, without resorting to external databases, one of the limitations found in similar studies. Regarding record linkage, we adopt deep learning models for semantic address matching, namely pretrained language models such as BERT or one of its variants. We train a BERT-based model from scratch and compare it with a novel vocabulary-free approach, based on ByT5, which shows competitive results in terms of accuracy. To further optimize models’ implementation, we adopt strategies such as automatic labelling of training datasets combined with synthetic datasets generation and in-batch negatives loss to minimize human effort and optimization methods such as automatic mixed precision to reduce computational overhead. As further developments, we propose the use of new generation transformer-based models, a privacy-preserving temporal record linkage approach and the optimization of algorithms using evolutionary coding agents such as AlphaEvolve.
- Indoor air quality management systems: A Mixed-methods Approach to Behavioral Drivers, Feature Use, and Humanistic Outcomes in EuropePublication . Veiga, Inês Ferreira dos Santos Botelho; Oliveira, Tiago André Gonçalves Félix de; Naranjo-Zolotov, Mijail JuanovichThis PhD thesis lies at the intersection of information systems, environmental science, and social sciences, examining how citizens adopt and use indoor air quality management systems (IAQMSs) to support sustainable, healthy indoor living. Although IAQMSs research has shown clear technical benefits, such as improved pollutant control and energy efficiency, the field still offers limited understanding of the behavioral side: why citizens adopt IAQMSs, how they use their features in everyday life, what motivates or demotivates progression in the adoption journey, and whether use is perceived to generate humanistic outcomes such as comfort, wellbeing, healthy living, and sustainable living. These gaps are particularly evident in the European context, where cross-country evidence remains limited. In response, this thesis aims to advance understanding of the drivers, barriers, use patterns, and outcomes of IAQMSs’ adoption. It does so through a sequential exploratory mixed-methods design comprising five papers: a meta- and weight-analysis of the IoT healthcare adoption literature; exploratory interviews with experts and consumers; a cross-sectional survey of 2,800 participants across seven European countries analyzed using PLS-SEM; and follow-up qualitative interviews to support interpretation and triangulation. The findings show that perceived severity consistently drives protection motivation, whereas perceived vulnerability is non-significant; coping beliefs vary across countries, with self-efficacy more central in Germany and response efficacy and cost more central in Portugal. Response efficacy, intuitiveness, and hedonic motivation strengthen comfort perceptions. Perceived benefits are the strongest driver of IAQ management feature use, while privacy concerns and information inaccuracy amplify barriers. Finally, health, technological, and social beliefs drive feature use, which in turn supports healthy living and sustainable living. Overall, the thesis advances knowledge by reframing IAQMSs as socio-technical systems, integrating protection motivation theory, dual factor theory, cost-benefit trade-off, and belief-action-outcome perspectives, and linking feature-level use to humanistic outcomes in a multi-country European context.
- Artificial Intelligence-Enabled Conversational Agents in Healthcare: Acceptance, Engagement, and ImplementationPublication . Yang, Yanrong; Oliveira, Tiago André Gonçalves Félix de; Tavares, Jorge Manuel Santos FreireArtificial intelligence (AI)-enabled conversational agents (CA) have increasingly been applied in health and healthcare contexts to support well-being, mental health, and access to digital services. Despite their growing adoption, limited understanding remains regarding how users accept, engage with, and experience these systems across different cultural and healthcare settings. Existing research is fragmented, with insufficient integration of theoretical models, limited cross-country evidence, and a lack of insight into real-world implementation challenges. In response to these gaps, the objective of this doctoral thesis is to systematically examine user acceptance, engagement, and implementation of AI-enabled well-being and healthcare chatbots. Specifically, this research aims to (1) review and synthesize existing research on the acceptance and use of well-being CAs; (2) develop and validate theoretical models that explain user engagement with well-being CAs; (3) examine cross-country differences in user acceptance and engagement; and (4) explore implementation experiences, as well as the challenges, of AI CAs as digital healthcare solutions across different national contexts. To achieve these objectives, this study employed both quantitative and qualitative methods. An integrative literature review was conducted to synthesize prior research on the acceptance of well-being CAs. Quantitative survey studies were conducted to test new extended research models and examine user engagement across countries, including a comparative analysis between the United States and China. Additionally, qualitative methods were used to explore perceptions, experiences, and implementation challenges of AI-driven digital healthcare solutions. The findings demonstrate that user acceptance and engagement with AI-based chatbots are influenced by technological, psychological, and contextual factors, with notable cross-country differences. The results also highlight key challenges related to accessibility, trust, and implementation in healthcare contexts. This thesis contributes to the field by advancing theoretical understanding of user engagement with AI-based well-being chatbots, providing cross-national empirical evidence, and offering practical insights to inform the design, implementation, and governance of digital health technologies.
- Information Management in Educational Settings: A Multilevel Analysis of Technological Innovation and Learning Outcomes in the Brazilian AmazonPublication . Mendonça, Yuri Vidal Santiago de; Pinto, Diego CostaThis thesis investigates the role of technology in education through a multi-level analytical framework comprising three complementary empirical studies, all situated within the context of public schools in the Brazilian Amazon. Adopting a thesis-bypublication format, the research progressively examines: (1) the macro-level systemic determinants of educational quality using machine learning and SHAP analysis; (2) the micro-level psychological mechanisms of technology adoption among teachers using PLS-SEM with an extended UTAUT model; and (3) the impact of a digital educational game on student learning outcomes through a quasi-experimental design. The first study (Chapter 3) applies decision tree-based machine learning models to an extensive dataset of Brazilian public schools, identifying that the number of computers per student, teachers' length of service, broadband internet access, and investment in technological training are the variables with the greatest predictive power for educational quality (R² = 0.8991). The second study (Chapter 4) employs Partial Least Squares Structural Equation Modelling (PLSSEM) with a sample of 311 educators from the Brazilian Amazon, demonstrating that prior technological experience functions as a behavioural antecedent — rather than merely a moderator — that shapes performance expectations (β = 0.172), social influence (β = 0.459), and facilitating conditions (β = 0.522), which in turn drive adoption of the Metaverse as an educational tool. The third study (Chapter 5) evaluates the efficacy of a digital educational game through a quasi-experimental design with 157 fifth-grade students, providing exploratory evidence that game users showed greater improvement in mathematics grades (average increase of 12%) compared to non-users (average decrease of −1.0%). Together, the three studies provide a multilevel account of technology adoption in education from policy-relevant macro indicators, through teacher-level psychological processes, to student-level learning impacts. The findings demonstrate that effective digital transformation in education requires strategic alignment between systemic infrastructure, teacher readiness, and targeted pedagogical interventions. The thesis contributes to Information Management and Educational Technology by offering empirical evidence and practical frameworks for educational policy in resource constrained settings.
- Energy and Data Science: Evaluating the Energy Performance of Buildings with Machine LearningPublication . Anastasiadou, Maria; Santos, Vítor Manuel Pereira Duarte dos; Dias, José Miguel de Oliveira Monteiro SalesThe problems of improving the energy performance of existing buildings, reducing energy consumption, and enhancing indoor comfort, with their numerous consequences, are well known. Considering increasing urbanisation and climate change, governments are defining strategies to enhance and measure the energy performance and efficiency of buildings. This work aims to improve the energy performance and efficiency of buildings by utilising artificial intelligence and deep learning to analyse energy performance certification data. This study has the following two main objectives. First, to perform automatic classification of the energy performance certification of buildings, analysing energy performance certification data, and second, to perform automatic proposals of energy-efficient retrofitting measures to improve the energy performance of buildings whose energy performance has been classified by achieving the first objective. This work bridges the gap between predictive models and their interpretability, supporting stakeholders, policymakers, and the building sector in making data-driven decisions for energy-efficient retrofitting and contributing to climate resilience in increasingly urbanised environments.
- Enhancing Ecosystem-based Disaster Risk Reduction Through Geoinformatics: Integrating Ecological Factors into Assessment PracticesPublication . Broquet, Melanie; Cabral, Pedro da Costa Brito; Campos, Felipe Siqueira eEcosystem-based Disaster Risk Reduction (Eco-DRR) leverages ecosystem conservation and restoration to mitigate natural disaster risks by providing regulatory services that reduce their intensity and lower the vulnerability of exposed communities and ecosystems. Despite growing recognition, especially after the 2004 Indian Ocean tsunami, Eco-DRR faces key barriers: limited consensus on ecosystem effectiveness, inconsistent methodologies, data scarcity, and the absence of standardized frameworks that integrate ecological factors into disaster risk assessments. This study addresses these gaps by using landslide hazard as a case study to strengthen the credibility and acceptance of Eco-DRR through empirical evidence and improved assessment practices. Three inter-connected objectives guided the work: (1) identifying ecological factors relevant for landslide susceptibility assessment (LSA) through literature review; (2) examining the relationship between Land Use/Land Cover (LULC) and habitat quality as indicators of hazard-prone landscapes using the InVEST Habitat Quality model; and (3) testing whether integrating ecological variables into LSA frameworks improves predictive performance using Random Forests. Findings show that eco-environmental factors, especially dynamic ones, remain underutilized in LSAs. LULC change was strongly correlated with ecological degradation, supporting the use of integrative indicators such as habitat quality for characterizing vulnerable landscapes. Integrated models combining structural and ecological variables, particularly dynamic ones, significantly outperformed conventional LSA models. These results confirm that eco-environmental variables play a critical role in shaping landslide susceptibility and should be systematically integrated into risk assessments. Overall, this research strengthens Eco-DRR’s scientific foundation by moving beyond static, hazard-centric approaches. It introduces evidence-based methodologies that are applicable even in data-scarce contexts, replicable across settings. By promoting cross-disciplinary integration and efficiency, the work helps bridge the knowledge–action gap, enhances policy relevance, and underscores ecosystems as critical assets whose protection and restoration are essential for breaking the cycle of degradation and disaster risk.
- Understanding the drivers of academic achievement: A multi-method approachPublication . Afonso, Ana Beatriz Antunes; Jesus, Frederico Miguel Campos Cruz Ribeiro deEducation is a fundamental driver of social mobility, sustainable development, and economic growth. Yet, despite its importance, the determinants of academic achievement (AA) remain contested, with fragmented findings often based on limited sample data. This work addresses this gap by leveraging administrative records from virtually all Portuguese public high school students, complemented by a targeted survey, to provide a comprehensive and context-sensitive analysis of AA. Rather than relying on isolated case studies, this thesis follows a multi-phase design that progressively deepens our understanding of AA. It begins by mapping global evidence on AA drivers, then examines virtually every student in the Portuguese high school system to assess how unprecedented eventssuch as the COVID-19 pandemic and regional disparities shape student outcomes. Finally, it integrates primary data to uncover how family environments, in particular parental involvement, interact with socioeconomic conditions during the transition to higher education. Several consistent findings emerged across the studies. Among those, socioeconomic status proved to be one of the strongest predictors of AA. The COVID-19 pandemic deepened existing inequities and altered the relative importance of different success factors. Regional disparities also became evident, with rural and urban students demonstrating distinct needs linked to unequal access to resources. Finally, parental involvement played a crucial role, not only exerting a direct influence on student outcomes but also moderating the effects of socioeconomic conditions. This thesis delivers a unique, comprehensive, large-scale analysis of AA in Portugal using the entire public secondary school population. It demonstrates the added value of machine learning over traditional methods in handling large-scale educational data. It generates actionable insights aligned with international policy frameworks such as the United Nations’ fourth Sustainable Development Goal. These contributions advance theoretical understanding while offering practical guidance for the design of more inclusive and equitable education systems.
- Advanced Machine Learning for Building Energy Efficiency: Integrating Predictive Models and Optimization Techniques for Smarter Energy Management and Strategic DecisionsPublication . Almeida, Fernando Pedro Silva; Castelli, Mauro; Côrte-Real , Nadine Evangelista de PinhoBuilding operations account for a significant portion of global energy consumption and carbon emissions, with heating, ventilation, and air conditioning (HVAC) systems being among the most energy-intensive components. Addressing inefficiencies in HVAC operations is crucial for achieving energy savings, reducing greenhouse gas emissions, and meeting sustainability goals, such as those outlined in the Paris Agreement, the EU’s Energy Performance of Buildings Directive (EPBD), and the REPowerEU plan. This study presents a comprehensive framework for forecasting, optimizing, and controlling space heating and cooling energy consumption in buildings using a combination of machine learning (ML), deep learning (DL), and reinforcement learning (RL) techniques. The research evaluates a broad range of ML and DL algorithms, including XGBoost, Random Forest, Support Vector Regression, Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer models, for their effectiveness in predicting space heating and cooling loads. These models are trained on real-world operational and meteorological data collected from the European Central Bank (ECB) building and demonstrate improved accuracy over traditional methods, mainly when feature selection includes localized weather conditions and building-specific variables. For space heating consumption, XGBoost achieved an R² of 0.966. At the same time, Random Forest consistently outperformed other models in cooling load prediction across multiple system types, such as Cooling Ceiling, Cooling Ventilation, Free Cooling, and Total Cooling. In addition to predictive modeling, the study develops a recommendation system based on LSTM networks to support energy efficiency decisions across space heating and selected cooling systems. The system provides hourly and daily forecasts, allowing energy managers to adjust operations dynamically. To enhance interpretability, OpenAI’s GPT4 model is integrated to offer contextual explanations of time-series graph outputs, facilitating non-technical understanding and informed decision-making. The feasibility, effectiveness, accuracy, and reliability of this natural language–based operational decision support and recommendation component are intended to be evaluated through enduser studies, which are identified as part of future work. The work further addresses the balance between energy efficiency and thermal comfort by utilizing DL-based forecasting models for multi-zone temperature and space heating consumption. A two-stage optimization process ensures occupant comfort (typically within 21–23°C in winter) while minimizing heating energy use, with LSTM and Transformer models achieving up to 21% reduction in heating demand compared to actual consumption, as calculated by comparing optimized heating schedules against historical baseline energy use over the same period. This reduction is validated across multiple building zones and weather conditions, confirming the effectiveness of the predictive optimization framework. Finally, a deep reinforcement learning framework is proposed to enable real-time adaptive control of HVAC systems. Among the tested models, Deep Deterministic Policy Gradient (DDPG) achieved the lowest comfort violations and temperature instability, outperforming TD3 and D-SAC, and demonstrating strong potential for practical deployment in Building Energy Management Systems (BEMS). This study contributes robust, scalable, and interpretable methodologies for data-driven energy management in buildings. It provides actionable solutions that not only enhance forecasting and operational efficiency but also support broader environmental and institutional objectives in the context of innovative, sustainable building design and management.
- Project Governance: Examining the Role of PMOs and PMIS Impact in Enhancing Organizational Project ManagementPublication . Monteiro, António José Vieira Póvoa; Santos, Vítor Manuel Pereira Duarte dos; Varajão, João Eduardo Quintela Alves de SousaOrganizational Project Management (OPM) has become essential for effective project governance by aligning strategic goals with project execution, particularly through organizational structures such as Project Management Offices (PMOs). However, the diversity of PMO configurations and their evolving role within increasingly complex and digitalized environments present significant challenges for both theory and practice. This research explores the contribution of PMOs to OPM by analyzing their typologies, functions, and their interaction with project management information systems (PMIS). The investigation unfolds in three phases. The first phase involved a systematic review of the literature to consolidate existing PMO typologies and types, identifying 16 typologies and 60 distinct PMO types. This phase revealed the dynamic and heterogeneous nature of PMOs and the lack of consensus regarding their functional boundaries. The second phase examined the evolution of PMO functions over the past two decades. Through literature analysis and a case study in a large organization, this phase confirmed the continued relevance of core PMO functions, such as monitoring performance and standardizing methodologies, while identifying emerging functions including stakeholder management, vendor coordination, and operational excellence in AI-driven projects. In the third phase, the research addressed the intersection between organizational structures and project tools. A conceptual model was developed and tested to evaluate the moderating role of PMOs in the relationship between PMIS use and project manager performance. Structural equation modeling (SEM) was conducted to assess the validity and reliability of the measurement model and to evaluate the hypothesized structural relationships within the conceptual model. The findings indicate the importance of establishing well-structured project management practices with technology, ensuring seamless alignment between organizational processes and technology. The findings also indicate that the presence of PMOs strengthen the effectiveness of PMIS, enhancing project decision-making and execution. Overall, this research contributes to the understanding of OPM by offering a consolidated and updated view of PMO configurations and functions, while also highlighting the importance of aligning governance structures and digital systems to improve organizational project outcomes.