http://hdl.handle.net/10071/44 Wed, 13 May 2026 20:54:38 GMT 2026-05-13T20:54:38Z http://hdl.handle.net/10071/37216 Título próprio: Prosociality in cyberspace: Developing emotion and behavioral regulation to decrease aggressive communication Autoria: Veiga Simão, A. M.; Ferreira, P.; Pereira, N.; Oliveira, S.; Paulino, P.; Rosa, H.; Ribeiro, R.; Coheur, L.; Carvalho, J. P.; Trancoso, I. Resumo: Different forms of verbal aggression are often present in cyberbullying, which may impair executive function skills that enable the regulation of emotions and behavior. Emotion and behavioral regulation has been associated with better social adjustment and more positive interactions between peers. This study aimed to understand if fostering emotion and behav- ioral regulation strategies could decrease aggressive communication. A quasi-experimental longitudinal design, based on a Twitter client mobile application, with pre-posttest measures was used. For the application, we explored different machine learning approaches, including computational intelligence methods. Multilevel linear modeling and frequency analyses were performed. A convenience sample of 218 adolescents (Mage = 14.67, SD = 0.84, 53% female) participated in the study. Results suggest that a Twitter client mobile application intervention based on emotion and behavioral regulation strategies may help decrease adolescents’ aggressive communication. Moreover, female and male participants who used the digital application tended to present distinct trajectories over time with regard to searching for information concerning prosocial behavior. These findings suggest that digital tools resorting to emotion and behavioral regulation strategies may be effective in reducing an aggressive communication style amongst adolescents, and consequently, promote resource seeking to engage in prosociality. These results can be significant for the design of intervention programs against cyberbullying. Fri, 01 Jan 2021 00:00:00 GMT http://hdl.handle.net/10071/37216 2021-01-01T00:00:00Z http://hdl.handle.net/10071/37065 Título próprio: Tailored laser wakefield acceleration for decaying particles Autoria: Badiali, C; Almeida, R.; Malaca, B.; Fonseca, R.; Silva, T.; Vieira, J. Resumo: We introduce a plasma wakefield acceleration scheme capable of boosting initially subrelativistic particles to relativistic velocities within millimeter-scale distances. A subluminal light pulse drives a wake whose velocity is continuously matched to the beam speed through a tailored plasma density, thereby extending the dephasing length. We develop a theoretical model that is generalizable across particle mass, initial velocity, and the particular accelerating bucket being used, and we verify its accuracy with particle-in-cell simulations using laser drivers with energies in the joule range. Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/10071/37065 2026-01-01T00:00:00Z http://hdl.handle.net/10071/36168 Título próprio: Aprendizado por transferência para correção automática de redação Autoria: Silveira, I. C.; Ribeiro, E.; Mamede, N.; Baptista, J. Resumo: A tarefa de Correção Automática de Redação tem despertado crescente interesse na área de processamento de texto em português. Entre os conjuntos de dados disponíveis, destaca-se um corpus de redações narrativas produzidas por alunos do 5º ao 9º ano do ensino fundamental no Brasil. Essas redações são avaliadas segundo quatro competências: registro formal, coerência temática, estrutura retórica narrativa e coesão textual. Este trabalho explora a criação de um sistema baseado em conhecimentos derivados de outro dataset (desenvolvido com base em textos produzidos para o ENEM) e de outras tarefas (cálculo de complexidade textual e análise de legibilidade). O sistema desenvolvido combina modelos neurais, características (features) curadas calculadas por programas de análise textual e seleção de features em um modelo de Aprendizado em Dois Estágios. Com isso, foi possível elevar a performance em relação ao estado-da-arte, nomeadamente, em 9% para a primeira competência, 5,5% para a terceira e 8,9% para a quarta. Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/10071/36168 2025-01-01T00:00:00Z http://hdl.handle.net/10071/35734 Título próprio: Enhanced multiple instance learning for breast cancer detection in mammography: Adaptive patching, advanced pooling, and deep supervision Autoria: Sarwar, Fareeha; Garrido, Nuno Miguel de Figueiredo; Sebastiao, Pedro; Silveira, Margarida Resumo: This paper addresses the challenge of weakly supervised learning for breast cancer detection in mammography by introducing an Enhanced Embedded Space MI-Net model with deep supervision. The framework integrated adaptive patch creation, convolution feature extraction, and pooling methods -max, mean, log-sum-expo, attention, and gated attention pooling - evaluated in three MIL models, Instance Space mi-Net, Embedded Space MI-Net and Enhanced Embedded Space MI-Net. A key contribution is the incorporation of deep supervision, improving feature learning across network layers and enhancing bag-level classification performance. Experimental results on the CBIS / DDSM dataset demonstrate that the Enhanced MI-Net model achieves the highest AUC of 86% with attention pooling. This work addresses the gap in leveraging MIL techniques for high-resolution medical imaging without requiring detailed annotations, offering a robust and scalable solution for breast cancer detection.Clinical Relevance-This study highlights the potential of MIL-based models with attention pooling to accurately detect breast cancer in mammographic images without requiring detailed ROI annotations, offering a scalable and efficient diagnostic tool for clinical practice. Tue, 01 Jul 2025 00:00:00 GMT http://hdl.handle.net/10071/35734 2025-07-01T00:00:00Z