Browsing by Issue Date, starting with "2025-03"
Now showing 1 - 8 of 8
Results Per Page
Sort Options
- Identification of depressing tweets using natural language processing and machine learning: application of grey relational gradesPublication . Ullah, Wusat; Oliveira-Silva, Patrícia; Nawaz, Muhammad; Zulqarnain, Rana Muhammad; Siddique, Imran; Sallah, MohammedDepression is a global public health concern that affects millions of people worldwide. Social media platforms, where individuals connect and share personal data, have emerged as potential sources for mental health detection. This study explored the use of computational models to identify individuals with depression based on Twitter posts. We retrieved and cleaned 1.6 million tweets using Natural Language Processing (NLP) techniques for feature extraction. The Grey Relational Grade (GRG) technique was applied to investigate the association between likes and shares of Twitter posts. Furthermore, the significant values of GRG in both cases, when data is limited and when data is large, represent that GRG provides better results at large data sets. The equal distri bution and selection approach (EDSA) can extract a small sample to describe the large data set and apply the GRG technique. Subsequently, we applied various machine learning models to classify user tweets into "stressed" or "not stressed" categories. These models achieved promising results, demonstrating high accuracy, precision, recall, and F1-score. Specifically, Logistic Regression, Support Vector Machine, XGBoost Classifier, and Random Forest Classifier yielded accuracies of 96, 95, 96, and 97%, respectively. These findings suggest the potential of social media data and computational models for mental health detection, thus opening avenues for further research and development.
- More than words: conceptualizing narrative computational thinking based on a multicase studyPublication . Schlauch, Michael; Sylla, Cristina; Gil, MaitêThis paper presents an investigation that compares and analyzes the interactions of three groups of pre-and-primary school children with three different storytelling systems. We identify emerging patterns through which they engaged in what we refer to as narrative computational thinking. The latter describes broadened aspects of narrative literacy practices that are linked to computational thinking. By applying a multicase study approach and through various vignettes, we illustrate how children applied computational thinking to understand and influence the narrative possibilities offered by the different tools. Our results illustrate circumstances under which digital storytelling activities provide a favorable basis for narrative computational thinking, and that when computational thinking functions as a scaffold for story creation, it encourages a blend of creativity and computational thinking, providing a compelling approach to introducing emerging digital literacies to young children in a narrative context.
- The volatility puzzle of the beta anomalyPublication . Barroso, Pedro; Detzel, Andrew; Maio, PauloThis paper shows that leading theories of the beta anomaly fail to explain the anomaly's conditional performance. Abnormal returns and Sharpe ratios of betting-against-beta (BAB) factors rise following months with below-median realized volatility, even controlling for mispricing, limits to arbitrage, lottery preferences, analyst disagreement, and sentiment. Moreover, the leverage constraints theory counterfactually predicts that market and BAB Sharpe ratios increase with volatility. We further show that institutional investors shift their demand from high- to low-beta stocks as volatility increases, and the resulting price impact is sufficient to explain the difference in abnormal BAB returns between high- and low-volatility states.
- A digital tool for self-reporting cardiovascular risk factors: the RADICAL studyPublication . Santos, José Ferreira; Castela, Inês; Madeira, Sara Gamboa; Furtado, Sofia; Pereira, Hugo Vieira; Teixeira, Diana; Dores, HélderAims: Cardiovascular diseases remain the leading cause of death worldwide. Risk stratification and early interventions are essential to overcome this reality. The RADICAL Study (Risk Assessment via Digital Input for Cardiovascular And Lifestyle Factors) aimed to evaluate the prevalence of self-reported cardiovascular risk factors in individuals without known cardiovascular disease using a digital tool. Methods and results: A digital self-reported cardiovascular risk stratification tool, comprising 23 questions about classical and lifestyle cardiovascular risk factors, was completed by 4149 individuals aged 40–69 years (median age 53.0 [47.0; 60.0] years; 78 % women). Among the cardiovascular risk factors, 40.9 % reported hypercholesterolemia, 26.8 % hypertension, 17.3 % smoking, 5.8 % diabetes, 58.4 % physical inactivity, 19.4 % obesity, 33.7 % sleep less than 7 h/night, and 12.1 % had composite dietary risk factors. Most of the participants (89.9 %) referred having at least one of the eight cardiovascular risk factors. Women had 27 % higher odds of having at least one cardiovascular risk factor compared to men (OR = 1.27, 95 % CI [1.00, 1.60]). Participants aged 50–59 years also had higher odds of having at least one CV risk factor compared to those aged 40–49 years (OR = 1.35, 95 % CI [1.07, 1.70]). Conclusion: The RADICAL Study reveals a high prevalence of cardiovascular risk factors in adults without known cardiovascular disease. Beyond the relevance of traditional risk factors, such as hypercholesterolemia and hypertension, the results regarding physical activity, dietary and sleeping habits are concerning. A self-reported cardiovascular risk identification digital tool could be feasible and help to improve cardiovascular prevention.
- The ECB’s APP’s impact on non-financial firms’ cost of borrowing and debt choicePublication . Kanda, Joana F.; Pinto, João M.; Silva, Beatriz P.We examine the impact of the ECB’s asset purchase programmes on euro area non-financial firms’ cost of borrowing and their choice between corporate bonds and syndicated loans. Our findings indicate that the Corporate Sector Purchase Programme (CSPP) reduced spreads for both eligible and non-eligible corporate bonds, and that ECB purchases of covered bonds positively affected corporate bond spreads. The CSPP also compressed spreads across all syndicated loans, irrespective of eligibility. We find evidence supporting a “cost of borrowing channel” for covered bonds under the first programme and asset-backed securities, indicating that syndicated loan spreads reflect banks’ borrowing costs in the bond market. Additionally, our results reveal that the CSPP significantly influenced firms’ debt financing choices, with these effects being more pronounced for non-switchers.
- Stressors and expected performance of soccer athletes: the role of sport confidence and cognitive appraisalPublication . Morais, Catarina; Simães, Clara; Gomes, A. Rui; Gonçalves, Beatriz MartinsThis study aimed to provide a framework for how athletes evaluate stress before a competition and how stress relates to cognitive appraisal, sport confidence, and expectations of performance. Participants were 327 youth male athletes, aged 15–19 years (M = 16.90; SD = 1.00), who competed in the Portuguese National Football League and completed a questionnaire 24–48 hr before their match, using the critical incident methodology. Results revealed that opponents were the main source of stress for athletes and that the more athletes stress about their opponents, the more they tend to perceive the situation as threatening (and less challenging), the lower their perceptions of coping and sport confidence which, in turn, predicted lower expectations of individual and collective performance. In sum, perceiving the stressful situation as either a challenge or a threat predicts young athletes’ sport confidence and, consequently, expected performance when dealing with stressful competitive situations.
- Nurses and allied professionals’ engagement in clinical research-in-practice: a statement of the Association of Cardiovascular Nursing & Allied Professions of the European Society of CardiologyPublication . Fredericks, Suzanne; Sanders, Julie; Back, Maria; Desteghe, Lien; Gomes, Ana; Marques-Sule, Elena; Simpson, Maggie; Hendriks, Jeroen M.Many nurses and allied professionals (NAPs) lack the skills, knowledge and confidence to engage in conducting and implementing research. This statement describes the importance of NAPs' involvement in clinical research within the context of cardiovascular care. The existing gaps, barriers and enablers to NAPs involvement in research as a potential response to workforce issues in these professions as well as to contribute to excellence in patient care delivery and associated outcomes are identified. Specifically, career development pathways for NAPs are discussed. Finally, potential future directions for NAP research in clinical practice are provided.
- Os desenhos ou modelos como fator de inovação : o problema da paródiaPublication . Pinto, Rebeca de Oliveira Neves Macedo; Vasconcelos, Pedro Leitão Pais deA paródia, enquanto imitação com propósito humorístico de um desenho ou modelo, tem de se inspirar nas características da aparência do produto que utiliza. No entanto, a paródia deve possuir carácter próprio, de modo a diferenciar-se do produto que evoca. Quanto a isto, compreende-se o desagrado do titular de um desenho ou modelo em ver a sua criação como objeto de críticas que poderão perturbar o seu direito de exclusivo e, consequentemente, a sua atividade comercial. Desta forma, a presente dissertação tem como objetivo compreender de que modo é que a paródia é admissível no âmbito deste regime e ainda, se existe possibilidade para a proteção de uma paródia enquanto desenho ou modelo.