Ciências e Tecnologia / Sciences and Technology
Permanent URI for this community
Browse
Browsing Ciências e Tecnologia / Sciences and Technology by Field of Science and Technology (FOS) "Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática"
Now showing 1 - 7 of 7
Results Per Page
Sort Options
- Does fake news have feelings?Publication . Laroca Mendes Pinto, Herbert; Rocio, Vitor; Cunha, AntónioFake news spreads rapidly, creating issues and making detection harder. The purpose of this study is to determine if fake news contains sentiment polarity (positive or negative), identify the polarity of sentiment present in their textual content and determine whether sentiment polarity is a reliable indication of fake news. For this, we use a deep learning model called BERT (Bidirectional Encoder Representations from Transformers), trained on a sentiment polarity dataset to classify the polarity of sentiments from a dataset of true and fake news. The findings show that sentiment polarity is not a reliable single feature for recognizing false news correctly and must be combined with other parameters to improve classification accuracy.
- Enhancing digital libraries through NLP and recommender systems: current trends and future prospects with large language modelsPublication . Cardoso, Heike da Silva; Rocio, VitorIn an era characterized by rapid proliferation of scientific publications and overwhelming volumes of digital content, researchers, students, and faculty members face significant challenges in identifying literature relevant to their academic pursuits. This saturation of information has heightened the need for advanced Recommender Systems within university libraries, tailored specifically for navigating and discovering scientific literature. This paper proposes leveraging insights from librarians’ direct interactions with users to adapt existing Recommender Systems, augmented with NLP and LLMs, to better serve the specific needs of academic researchers. It should streamline the research process by delivering precise, relevant, and personalized literature recommendations, centered on a curated database of bibliographic information.
- Enhancing recruitment with LLMs and chatbotsPublication . Novais, Liliana; Rocio, Vitor; Morais, A. JorgeTraditional approaches in the competitive recruitment landscape frequently encounter difficulties in effectively identifying exceptional applicants, resulting in delays, increased expenses, and biases. This study proposes the utilisation of contemporary technologies such as Large Language Models (LLMs) and chatbots to automate the process of resume screening, thereby diminishing prejudices and enhancing communication between recruiters and candidates. Algorithms based on LLM can greatly transform the process of screening by improving both its speed and accuracy. By integrating chatbots, it becomes possible to have personalised interactions with candidates and streamline the process of scheduling interviews. This strategy accelerates the hiring process while maintaining principles of justice and ethics. Its objective is to improve algorithms and procedures to meet changing requirements and enhance the competitive advantage of talent acquisition within organisations.
- Face-to-face interactions estimated using mobile phone data to support contact tracing operationsPublication . Cumbane, Silvino; Gidófalvi, Gyözö; Cossa, Osvaldo; Madivadua Júnior, Afonso; Branco, Frederico; Sousa, NunoUnderstanding people’s face-to-face interactions is crucial for effective infectious disease management. Traditional contact tracing, often relying on interviews or smartphone applications, faces limitations such as incomplete recall, low adoption rates, and privacy concerns. This study proposes utilizing anonymized Call Detail Records (CDRs) as a substitute for in-person meetings. We assume that when two individuals engage in a phone call connected to the same cell tower, they are likely to meet shortly thereafter. Testing this assumption, we evaluated two hypotheses. The first hypothesis—that such co-located interactions occur in a workplace setting—achieved 83% agreement, which is considered a strong indication of reliability. The second hypothesis—that calls made during these co-location events are shorter than usual—achieved 86% agreement, suggesting an almost perfect reliability level. These results demonstrate that CDR-based co-location events can serve as a reliable substitute for in-person interactions and thus hold significant potential for enhancing contact tracing and supporting public health efforts.
- Formação Flash sobre IA Generativa: algumas notas para o desenvolvimento profissional docentePublication . Rocio, Vitor; Cruz, Elisabete; Freitas, João Correia de; Pereira, Carolina
- Professional training for effective adoption of Generative AI in the corporate world: bridging the gapPublication . Guedes, Fernando; Rocio, Vitor; Martins, PauloThis position paper emphasizes the critical role of professional training in facilitating the effective adoption of Generative AI (GenAI) in the corporate world. GenAI, with its ability to create new content from existing data, holds immense potential for transforming business processes, enhancing decision-making, and driving innovation. However, the adoption of GenAI faces significant challenges, including a shortage of skilled professionals, high implementation costs, data privacy concerns, and the complexity of integrating these technologies into existing systems. To address these challenges, this paper highlights the importance of comprehensive education and training programs tailored to equip employees with the necessary skills and knowledge. Such programs should focus on developing technical competencies and understanding the operational implications of GenAI. By analyzing current literature and case studies, this paper identifies key strategies for effective training and outlines best practices for integrating GenAI into corporate environments. The findings underscore the need for a strategic approach to training that aligns with the evolving demands of AI-driven innovation. This includes continuous learning and development initiatives, the promotion of a culture of innovation, and the implementation of responsible AI practices. By investing in professional training, organizations can bridge the skills gap, mitigate risks, and fully leverage the transformative potential of GenAI technologies, ultimately gaining a competitive edge in the market. Through this comprehensive exploration, the paper advocates for the integration of robust training frameworks that support the sustainable adoption of GenAI, ensuring that businesses are well-prepared to navigate the complexities and opportunities of the digital age.
- Sistema de Classificação de Sinalética Gestual em competições de karatéPublication . Violante, Sónia Correia; Filipe, Vítor; Morais, A. Jorge; Rocha, Álvaro; Peñalvo, Francisco; Gonçalves, Ramiro; Garcia Holgado, Alicia; Moreira, FernandoEm contexto de Kumite (combate de Karate) propõe-se investigar um modelo de classificação da sinalética gestual do árbitro para atribuição de pontos, com recurso a Visão Computacional e técnicas de Aprendizagem Profunda. Foram realizadas três abordagens, todas tendo como base o recurso a modelos de Redes Neuronais Convolucionais (Convolutional Neural Network – CNN): Classificação de imagens com recurso a uma CNN; Deteção da pose humana com o modelo MoveNet; e a deteção e classificação de gestos com o modelo YOLOv5, via RoboFlow. A última abordagem obteve melhores resultados, com 100% de precisão para todas as classes, pelo que se testou a sua aplicação para a deteção e classificação dos gestos em vídeo.