Percorrer por autor "Antonio, Nuno"
A mostrar 1 - 6 de 6
Resultados por página
Opções de ordenação
- Improving trust in online reviews: a machine learning approach to detecting artificial intelligence-generated reviewsPublication . Ana Marta Santos; Antonio, NunoIn the hotel industry, social reputation is critical. Consumers increasingly rely on online reviews for accommodation decisions, making Artificial Intelligence (AI) generated fraudulent reviews a significant threat. Distinguishing between genuine and AI-generated reviews is essential for hotels to maintain credibility. This study creates a unique dataset of AI-generated reviews and combines vectorization methods with text-based features to build a Machine Learning model for identifying nongenuine reviews. Results show that incorporating text-based features significantly improves detection accuracy, and simpler vectorization methods can be effective for simpler datasets. This study contributes to academia by providing a novel methodology and publicly available dataset for further research, and to the hotel industry by enhancing credibility and consumer trust through better review filtering.
- Mapping information systems maturity: the case of the portuguese hospitality industryPublication . Sá, Gustavo; Antonio, NunoHospitality is a highly competitive market that struggles to improve its performance. The use of technology is a critical factor for more efficient performance. To understand decision-makers' perception of information systems' influence and importance in their organisations, we conduct a case study in Portugal. The objective was to assess information systems' maturity level of independent hotels and small hotel chains, mapping the level to the hotel's characteristics. In addition, this study explores the types of systems used and hoteliers' main factors, drivers, and limitations to invest in information systems' maturity. We examined 86 companies, representing a total of 195 hotels. The analysis design was done following the Network Exploitation Capability (NEC) model. We found that, generally, hoteliers consider that their companies take more advantage of technology and information systems than they really do. These findings emphasise the importance of the use of technology in hospitality performance and the lack of knowledge that hoteliers have on the subject.
- Navigating uncertainty: enhancing hotel cancellation predictions with adaptive machine learningPublication . Silvestre, Pedro; Antonio, Nuno; Carrasco, PauloAccurately predicting hotel booking cancellations is critical for hotel management, especially during volatile periods such as the COVID-19 pandemic. Prior work demonstrated that machine-learning (ML) models perform well on historical data, yet few studies test robustness under severe disruption. We evaluate ML classifiers trained on pre-pandemic data from four hotels and assess their adaptability to pandemic conditions (Study One). We then examine whether adding pandemic observations via a dynamic sliding-window approach improves accuracy (Study Two). Pre-pandemic models exhibit reasonable discrimination, but including pandemic-period data can raise the Area Under the Curve (AUC) by up to 5% points. A nine-month training window balances stability and responsiveness, capturing rapid shifts in booking patterns and customer behavior. Feature importance also changes: Lead time and other drivers show altered effects during the pandemic, underscoring the need for continuously updated models. Anchored in concept-drift theory, we interpret the pandemic as an abrupt shift in the cancellation decision boundary and show that sliding-window retraining together with interpretable diagnostics (e.g., the Lead time crossover threshold) provides a theoretically grounded blueprint for prediction under distributional change. Our results advocate scheduled retraining and lightweight drift diagnostics to sustain forecast accuracy and managerial actionability. For hotel managers and technology providers, the proposed approach supports proactive cancellation management, more reliable forecasting, and resilient operations in volatile markets, demonstrating the robustness of adaptive ML under conditions of extreme market volatility. The study advances theoretical understanding and practical applications by operationalizing concept-drift management in revenue-critical settings.
- Promoting sustainability through regional food and wine pairingPublication . Serra, Manuel; Antonio, Nuno; Henriques, Cláudia Helena; Afonso, Carlos M.Sustainable development has been growingly recognized as important in the scope of tourism and hospitality industry practices. Gastronomic tourism associated with regional food-and wine pairing helps the emerging of higher quality services and contributes to the sustainability of tourist destinations. This study presents a pairing model based on three Real-Time Delphi (RTD) questionnaires to allow experts to select and pair regional wines with regional foods. In the first questionnaire, the experts were asked to choose, by category, the most representative regional dishes from the Algarve region (Portugal). In the second questionnaire, for each dish, experts voted on the best regional wines for the dish. In the third questionnaire, experts made quantitative and qualitative analyses for each of the three most voted wines for each dish. The resulting pairing model of regional food and wines will be communicated to tourism professionals and the general public. By promoting the consumption of these pairings, we promote an efficient, socially fair, and ecologically sustainable local economy. At the same time, we stimulate the circular economy in tourism.
- Understanding risk factors of post-stroke mortalityPublication . Castro, David; Antonio, Nuno; Marreiros, Ana; Nzwalo, HipólitoStroke is one of the leading causes of death worldwide. Understanding the risk factors for poststroke mortality is crucial for improving patient outcomes. This study analyzes and predicts poststroke mortality using the modified Rankin Scale (mRS), a functional neurological evaluation scale. Several Machine Learning models were developed and assessed using a dataset of 332 stroke patients from Hospital de Faro, Portugal, from 2016 to 2018. The Random Forest model outperformed others, achieving an accuracy of 98.5% and a recall of 91.3. Twenty-four risk factors were identified, with stroke severity as the most critical. These findings provide healthcare professionals with valuable tools for early identification and intervention for high-risk stroke patients, enabling informed decision-making and customized treatment plans. This research advances healthcare predictive analytics, offering a precise mortality prediction model and a comprehensive analysis of risk factors, potentially improving clinical outcomes and reducing mortality rates. Future applications could extend to patient monitoring and management across various medical conditions.
- Youth associations and entrepreneurship: insights from case studies in PortugalPublication . Antonio, Nuno; Pinto, HugoThe development of skills for entrepreneurship among young people has attracted interest at various levels, as a way of overcoming many problems that affect this group in the areas of economic development and job creation. This article assumes that participating in a youth association enables young people to develop a series of skills, in particular, their entrepreneurial capacities. This study pays attention to the contributions of the participation in youth associations for the promotion of entrepreneurship. The investigation based on a qualitative approach, through comparative case studies in Portugal. It was possible to verify that youth associations assume a dual role, on the one hand contributing to the personal, social and professional development of its leaders, members and participants, and on the other hand, as a promoter of social transformation, particularly at the local level.