Publicações
Autores
Financiador
Organizações

Pesquisar

Explore também...
 

Entradas recentes

  • Item type: Publicação , Access status: Acesso restrito ,
    Service brand coolness and the desire to stay: The mediating roles of communal brand connection, pride, and anticipated guilt
    (2026-09-04) Lopes, Maria Marta de Melo Sousa; Loureiro, Sandra Maria Correia
    This dissertation investigates how the coolness dimensions (extraordinary/utilitarian, iconic, and popularity) of service brands influence consumers’ desire to remain with the brand, by analysing the mediating roles of communal brand connection, pride, and anticipated guilt. In a digital context where services such as Spotify and Uber have become part of consumers’ daily routines, it is essential to understand the relational and emotional mechanisms that sustain loyalty. Drawing on relational marketing, moral emotions, and engagement theories, the study proposes that brands perceived as cool strengthen communal brand connection, which in turn triggers moral emotions that positively influence the intention to stay with the brand. This research employed both quantitative and qualitative methods, using a questionnaire administered to Spotify and Uber users, with a sample size of 213, analysed through PLS‑SEM and SPSS, and a focus group with 8 participants, analysed manually without software assistance. The results show that brand coolness positively affects communal brand connection, which strongly influences pride and anticipated guilt. Both emotions contribute to consumers’ desire to remain with the brand, with pride emerging as the strongest mediator. The multigroup analysis further reveals no significant differences between hedonic and utilitarian services, indicating that service type does not moderate the relationship between coolness and communal brand connection. These findings suggest that, in today’s digital service landscape, the distinction between hedonic and utilitarian services is increasingly blurred, as both integrate functional and emotional elements. The results contribute to a deeper understanding of coolness in digital services and offer practical implications for brands seeking to strengthen long‑term consumer relationships. The main recommendations suggest that service brands should invest in strategies that reinforce perceptions of coolness and promote authentic communal bonds, as these strengthen moral emotions, which, in turn, significantly increase consumers’ desire to stay with the brand.
  • Item type: Item , Access status: Acesso aberto ,
    Early detection of at-risk university students using machine learning: A study of model performance in evolving academic environments
    (2025) Rodrigues, D.; Lopes, A. L.; Mauritti, R.; Roque Ferreira, M.; Pintassilgo, S.; Chova, Luis Gómez; González Martínez,Chelo; Lees, Joanna
    This study explores the early detection of at-risk students using machine learning (ML) models trained on historical academic data. We constructed two datasets from university enrollment records spanning the 2016/2017 to 2022/2023 academic years, focusing on first-time enrollees in their first curricular year. The first dataset included only pre-enrollment information available at the start of the academic year, while the second incorporated first-semester performance data. Each dataset was used to predict two target outcomes: academic success and dropout. We evaluated multiple ML models, including Random Forest, Support Vector Machine (SVM), Naïve Bayes, Decision Tree, AdaBoost, K-Nearest Neighbors (KNN), and Logistic Regression. To optimize model performance, we employed Optuna for hyperparameter tuning, conducting hundreds of trials per algorithm. The best-performing models were tested on two datasets: one from historical student data (2016/2017–2022/2023) and another from the 2023/2024 academic year, reflecting a real-world shift due to a newly implemented university intervention strategy aimed at providing personalized support for at-risk students. Although the intervention itself was not included as a model variable, it may have influenced student success and dropout rates in 2023/2024, potentially impacting model predictions. By comparing performance on pre- and post-intervention data, this study assesses the robustness and generalizability of ML-based early warning systems in dynamically evolving academic environments.
  • Item type: Item , Access status: Acesso aberto ,
    Digital transformation in Portuguese banking: Impact of the COVID-19 pandemic
    (2024) Fonseca, A.; Rodrigues, L. F.; Alturas, B.
    Purpose Currently, digital transformation is a process that cuts across different sectors of activity, including banks. One of the examples is the availability of products and services on digital channels. This study aims to identify the changes implemented in the digital channels of banks in Portugal that were driven by the COVID-19 pandemic, contributing to the acceleration of digital transformation. Design/methodology/approach The methods involve a qualitative approach, from the analysis of a selection of 30 results and accounting reports from ten banks between 2019 and 2021 using the Leximancer software to identify the main themes and concepts. Findings Four themes and 40 most relevant concepts were identified from the results of the analysis. In conclusion, banks have reinforced digital channels regarding products and services with apparent concerns associated with security. Research limitations/implications This article aims to contribute to two conceptual maps that allow us to understand the measures implemented by banks in digital channels during the pandemic. Practical implications This investigation aims to enable managers to define other initiatives within the scope of digital channels and enhance those already implemented. Originality/value The scientific articles identified and published so far do not specifically address the impact that the COVID-19 pandemic has had on the digital channels of banks in Portugal. The originality of this article arises from this gap identified regarding the absence of similar scientific studies. The pandemic is a new phenomenon that occurred for the first time in 2019 and globally, so it is essential to know the impacts on Portuguese banks.