NIMS: MagIC - Documentos de conferências internacionais
URI permanente para esta coleção:
Navegar
Entradas recentes
- A longitudinal study of ERP system capabilities and valuePublication . Ciobanu, Anastasia; Ruivo, Pedro; Oliveira, Tiago; Neves, Joana; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management School; ElsevierThis study investigates the enduring significance of enterprise resource planning (ERP) systems and their contribution to business value, focusing on three core capabilities: ERP routinization, collaboration, and analytics. Grounded in the resource-based view (RBV), our research examines how these capabilities evolve over a five-year period (2015 to 2020) and jointly influence ERP value. The empirical evidence confirms that each capability exerts a positive effect on ERP value, yet their impact differs notably over time. Specifically, while analytics and routinization exhibit a gradual decrease in importance, collaboration experiences a marked decline if not actively maintained. These results highlight the need for consistent investments in daily ERP usage, coordinated cross-functional collaboration, and data-driven decision-making in order to maximize and sustain ERP value.
- AI Chatbots for Well-Being Adoption DriversPublication . Tavares, Jorge; Yang, Yanrong; Oliveira, Tiago; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); ElsevierThe global mental health sector lacks resources particularly in low- and middle-income countries. AI- chatbots are increasingly recognized as a promising resource to support mental health. However, the acceptance of AI chatbots in the field of mental health is still low. Our study aims to predict their usage, identifying the features which are more relevant for the prediction. An online survey was created in China with 400 valid responses collected. For our prediction exercise we used three Machine Learning algorithms: decision tree, logistic regression, and random forest. The accuracy of these algorithms ranged from 64-71%. Age was the most important feature to explain usage. Younger people value the compatibility of AI chatbots for well-being with their lifestyle, and older people are influenced by social factors to use them. Higher complexity can be an obstacle for AI chatbots for well-being use.
- Developing Conversational AI to Enhance the Tourist ExperiencePublication . Jardim, Bruno; Dona, Ricardo Montenegro; Neto, Miguel de Castro; Barnabé, Sandra; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS)Tourism in Porto has expanded considerably over the last decade, with the number of visitors doubling between 2009 and 2019 and continuing to rise in recent years. This rapid growth creates challenges for the sustainable management of tourist inflows and highlights the need for innovative, data-driven solutions that can both support visitors and relieve pressure on local infrastructures. In response, this study proposes the development of a conversational AI system specifically designed to assist tourists in their daily activities and improve their overall experience of the city. The conversational AI is based on a Retrieval-Augmented Generation (RAG) framework, which combines an information retrieval component with a generative model to deliver accurate, context-aware responses. To ensure reliability, the system draws on more than 7,000 documents from diverse sources, including cultural guides, tourism platforms, and official city websites. Several experiments were conducted to identify the best performing system configuration, testing different retrieval strategies, ranking methods, and model architectures. The final solution demonstrates high retrieval accuracy and generates responses that score strongly on semantic similarity and answer quality metrics. Overall, the study demonstrates the potential of conversational AI systems as valuable tools for urban destinations facing growing tourist demand. Beyond Porto, this work illustrates how data-efficient conversational systems can support sustainable tourism management, improve the visitor experience, and serve as scalable solutions for cities with similar challenges worldwide.
- Tourism Walkability IndexPublication . Areosa, Inês; Jardim, Bruno; Barnabé, Sandra; Neto, Miguel de Castro; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS)Walking plays a central role in how tourists experience cities, yet most walkability measures remain oriented toward residents and do not reflect the specific spatial behaviours, sensitivities, and motivations of visitors. Existing indices typically overlook the importance of cultural access, environmental comfort, and safety perceptions for tourist mobility. As a result, there is a need for tourism-specific approaches that can capture how walkability varies within cities and how it relates to tourist mobility patterns. This paper proposes the Tourism Walkability Index (TWI), a fully geospatial and street-level framework designed to quantify walkability from a tourist perspective. The TWI integrates three dimensions – accessibility to relevant points of interest, access to public and shared transport systems and comfort conditions shaped by infrastructure and environmental quality. These dimensions are operationalised using a pedestrian network with slope-adjusted travel times and geospatial datasets describing urban amenities, mobility services, and comfort-related variables such as lighting, pedestrianisation, heat exposure, air quality, noise and traffic safety. The TWI is applied to four cities in northern Portugal – Porto, Braga, Guimarães and Vila Real – representing contrasting data environments and urban morphologies. Across all cities, the TWI reveals a recurring spatial structure: historic centres emerge as the most walkable areas, while peripheral zones consistently score lower. The fine spatial resolution reveal micro-scale contrasts that broader neighbourhood metrics obscure, including highly accessible but low-comfort streets, and comfortable yet poorly connected areas. These patterns highlight opportunities for targeted interventions, improved tourist dispersal, and enhanced alignment between tourism mobility and urban liveability goals. The multi-city application further demonstrates that the TWI yields coherent results even when only open data are available, indicating that its conceptual structure is robust and transferable. By providing a replicable, open-source workflow and fine-grained urban diagnostics, the TWI offers a practical tool for integrating walkability into tourism planning and sustainable mobility management.
- Tourism Through the 15-Minute LensPublication . Oliveira, Rita; Pelliza, Candela S.; Jardim, Bruno; Barnabé, Sandra; Neto, Miguel de Castro; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS)The 15-minute city concept has become a cornerstone of modern urban planning. Despite its worldwide application, research has mostly focused on accessibility to essential services, while accessibility to tourism remains less explored. Tourism, key to urban identity, livability, and visitor management, needs to be considered within proximity planning. In this context, analysing travel times and accessibility to tourist locations across different travel modes represents a key opportunity to gain insight into how these shape cities. This study applies the 15-minute city framework to tourism, characterizing accessibility from a visitor’s perspective. Porto, Portugal, a city facing the impacts of massive tourism, is used as a pilot area to measure access to touristic amenities. Using the Porto open data portal, we compiled 290 points of interest across eight tourism categories. For every Base Reference Geographical Information (BGRI) cell, the Portuguese census tracts,we computed the centroid and generated network-based travel times to each amenity for walking, cycling, and driving. From the origin-destination matrices, we derived a set of 15-minute city indicators, namely minimum travel time required to reach the amenities and counts and percentage of amenities reachable within 5/10/15 minutes. Results show how accessibility patterns vary by parishes and travel mode and offer a reproducible base for urban planning and destination management. The outcomes reveal that accessibility to tourism is strongly centre-weighted: the historic centre offers short walking times and high amenity variety, while the eastern and northern edges face slower access and fewer choices. Trips starting from two central parishes reach 43% of amenities within a 15-minute walk, while trips originating in peripheral parishes typically reach only 5% to 9%. Cycling enhances accessibility by making accessible a variety of amenities across most parishes within 10 minutes and nearly citywide by 15 minutes. This work reframes 15-minute accessibility around tourism, providing a multimodal transportation assessment, translating analytics into actionable indicators. The framework supports policymaker in diversifying attraction availability in underserved areas, distributing visitor flows, and aligning cultural-access goals with livability agendas, promoting smart cities' development.
- From Human to MachinePublication . Maia, Rodrigo dos Reis; Bravo, Jorge Miguel; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management SchoolCorporate disclosure through earnings calls is a crucial channel for financial communication that enables stakeholders to evaluate corporate strategies. However, current methods for assessing disclosure are outdated or focused too much on sustainability, often overlooking financial transparency. This study introduces a novel, optimised scale designed to bridge this gap by encompassing the responsibilities of a company to various stakeholders. The scale development process, grounded in a conceptual framework and exploratory factor analysis, used data from 74 investors and analysts in Brazil. The findings reveal a refined three-dimensional structure for evaluating earnings calls, incorporating Artificial Intelligence, Disclosure, and ESG. This scale contributes to advancing corporate disclosure research and improving communication practices. Additionally, the study reveals that Brazilian investor attribute equal importance to both analysts and artificial intelligence when making investment decisions through conference calls.
- Improving coastal monitoring and forecasting systems through interoperable OGC API EDR-based data services [abstract]Publication . Dias, Telmo; Videira, Cesário; Lobo, Victor; Costa, Ana Cristina; Baptista, Márcia L.; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management SchoolEffective coastal monitoring and forecasting systems rely on the availability and timeliness of interoperable, standardized, and accessible marine data across observational, modelling and service layers. Fragmented data formats, legacy infrastructures, and non-standardized access mechanisms remain significant barriers to the seamless integration of ocean observations into operational monitoring and forecasting systems and downstream applications. This study presents the development of a standards-based data workflow designed to enhance interoperability, scalability, and facilitate marine data integration, through the adoption of international standards and best practices. The proposed approach focuses on establishing robust data flows that transform, validate, and harmonize heterogeneous datasets (e.g., in situ near-real-time observations and numerical model outputs) into NetCDF format. Standardized and programmatic access to these datasets is enabled though the OGC API Environmental Data Retrieval protocol, implemented using the pygeoapi platform. By adopting open standards and service-oriented architectures, this framework enables efficient spatio-temporal querying of ocean variables, facilitating their assimilation into forecasting systems, decision-support tools, and customized applications. In parallel, geoportal interfaces were updated to integrate the new OGC API EDR services, ensuring that interoperable data access is available both through machine-to-machine interfaces and user-friendly graphical tools, supporting a broad range of user profiles and promoting citizen involvement and ocean literacy. By addressing interoperability at the data, service, and user-interface levels, this work demonstrates how standardized data infrastructures are key enablers for improved, scalable, and sustainable coastal monitoring and forecasting capabilities.
- Validation of CCDC Use with Sentinel-2 Time Series for Deforestation Detection in PortugalPublication . Louro, Filipe; Costa, Hugo; Caetano, Mário; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management SchoolForest management planning and monitoring are complex tasks that require regular oversight. However, the widespread presence of smallholdings in Portugal and increasing rural abandonment make this task particularly challenging. The Continuous Change Detection and Classification algorithm is notable for enabling the analysis of trends in satellite image time series. While it has been widely used for continuous land cover change monitoring with Landsat data, it has seen limited application in Europe. The use of Sentinel-2 time series, offering higher spatial and temporal resolution and now covering a significant historical period, could be key to enabling CCDC for forest monitoring in Portugal and across Europe. This study aims to validate recently published parameter settings and processing optimizations for applying CCDC with Sentinel-2 data to detect deforestation events in Portugal. The methodology is compared against reference data on forestry activities provided by The Navigator Company. Results show strong agreement with the reference data, with eucalyptus stand harvest events detected with an F1-score of 0.86 and a detection lag of 19 days for 80%. There is no statistically significant difference in detection accuracy for smaller forest stands, suggesting the method is highly promising for monitoring in regions where smallholding forestry presents management challenges.
- The Psychological Hindrance of Threat Appeals in Green CSR CommunicationPublication . Young, Kai-Yi; Okazaki, Shintaro; Henseler, Jörg; Information Management Research Center (MagIC) - NOVA Information Management SchoolThis study investigates the effectiveness of threat versus efficacy appeals in green CSR communication using protection motivation theory. Findings from an experimental design reveal that efficacy appeals positively influence pro-environmental attitudes, while threat appeals backfire through perceived sustainability hypocrisy. Results highlight psychological hindrances to threat-based messaging, offering insights for sustainable communication strategies in business contexts.
- Socio-Economic Consequences of Generative AIPublication . Costa, Carlos J.; Aparicio, João Tiago; Aparicio, Manuela; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management SchoolThe widespread adoption of generative artificial intelligence (AI) has fundamentally transformed technological landscapes and societal structures in recent years. Our objective is to identify the primary methodologies that may be used to help predict the economic and social impacts of generative AI adoption. Through a comprehensive literature review, we uncover a range of methodologies poised to assess the multifaceted impacts of this technological revolution. We explore Agent-Based Simulation (ABS), Econometric Models, Input-Output Analysis, Reinforcement Learning (RL) for Decision-Making Agents, Surveys and Interviews, Scenario Analysis, Policy Analysis, and the Delphi Method. Our findings have allowed us to identify these approaches’ main strengths and weaknesses and their adequacy in coping with uncertainty, robustness, and resource requirements.