Procedia Computer Science最新文献

This paper presents an in-depth analysis of a Twitter ego network, focusing on the scientific community. Utilizing relative network analysis techniques, the study explores community structures, influencer dynamics, and network resilience. Key methodologies include community detection, centrality analysis, predictive modeling for link prediction and influence propagation, as well as resilience analysis. Results show distinct community formations, influential nodes, varying network resilience to disruptions. This comprehensive analysis provides valuable insights into the complex dynamics of scientific discourse on social media, emphasizing the importance of influential nodes and community structures in maintaining network integrity and facilitating information flow. This study will provide theoretical, methodological, and framework references for other social network analysis.

This paper seeks to explore the impact of gender and age diversity within the board of directors, as well as the appointment of a female CEO, on the return of assets (ROA) and Tobin Q of banks on a global scale. The study is motivated by the growing interest in how the quality of human capital within boardrooms affects the performance of banks, as well as the conflicting results of previous research on this topic. To conduct the study, panel regressions with fixed effects were employed as the research method. The sample consisted of 470 banks, including 146 banks from emerging markets, and data was collected from 2013 to 2023. The findings revealed that gender diversity within the board had a significant and negative impact on banks’ Tobin’s Q. Additionally, there was no significant relationship found between gender diversity and banks’ ROA, as well as between age diversity and both banks’ ROA and Tobin’s Q. The appointment of a female CEO harmed banks’ Tobin Q in emerging markets, but no significant influence was found on ROA and Tobin Q in banks in the developed world. As a result, it appears that banks’ investors do not view gender diversity as separate from other human capital issues within the boardrooms and may not derive significant financial benefits from gender and age diversity. These findings can be valuable for strategic controlling in evaluating the impact of human capital on the boards and executive branches of financial institutions.

The rise of interdisciplinarity has brought new challenges for engineering. The use of behavioral data and the need to look at engineering from a broader perspective require new instruments to measure these specificities. Thus, this study aims to present a platform of measurement scales related to the acceptance and use of accessible technology by Brazilian researchers. To this end, a design science study will be carried out to provide a platform of validated instruments. In order to support the platform, a theoretical basis was compiled, which is set out in this paper.

This exploratory qualitative study sought to identify the main technological gaps faced by digital influencers from generations X, Y, and Z. Using interviews with open questions, perceptions of nine Brazilian digital influencers from different areas and age groups were collected. The interviews, with an average duration of 40 minutes, addressed two blocks: the influencers’ profile and perception of the technologies used. The content analysis through a Similitude Tree created by the Iramuteq software revealed common gaps between generations, such as adaptation to new platforms, emotional control, search for engagement, and constant updating. Understanding these nuances across generations allows for tailored solutions to minimize technological challenges and promote digital inclusion and professional success for these women. Future studies should explore creating a structural equation model to test the standard dimensions found.

The area of data science knowledge responsible for dealing with this new reality is diffuse, including mathematics, statistics, computing, engineering, psychology, and administration, among many other areas that make up a new scenario that is still changing. Different models have emerged over the years to systematize the procedures to be followed. Among them, CRISP-DM (Cross Industry Standard Process for Data Mining) has become one of the most widespread in the industry. However, the lack of detailed instructions means the framework is often incorrectly used. Therefore, this research aims to present a utilitarian and didactic model based on the latest advances in the literature and through the lens of production engineering. In order to achieve this objective, exploratory research was carried out based on a systematic review and subsequent categorization of each of the CRISP-DM steps, detailing the authors’ contributions to each stage. In addition, it is proposed that guidelines from the areas of Quality Management and Risk Management be added to the subject, consolidating a useful and didactic model of relevance.

This paper delves into leveraging deep learning techniques, such as graph neural networks (GNNs), Transformer, and techniques in Large Language Models (LLMs), to enhance course recommendation systems in e-learning platforms. Recommendation methods have some short-comes in the case of online course with less information and choic less logic. Our research proposes novel algorithms that use graph collaborative filtering and sequential recommendation to improve recommendation accuracy and personalization. By analyzing user behavior patterns and course attributes, our approach aims to provide smarter and more efficient course recommendation services, ultimately enhancing learning outcomes and experiences in e-learning environments. This research not only contributes to the advancement of e-learning technology but also provides valuable insights for the broader application of deep learning in smart education.