https://repositorio.ufpb.br/jspui/handle/tede/5439 PPGI Mon, 20 Jul 2026 21:10:40 GMT 2026-07-20T21:10:40Z https://repositorio.ufpb.br/jspui/handle/123456789/38252 Título: Detecção e análise de dark patterns em plataformas de apostas no Brasil Autor(es): Lemos, Diego Oliveira de Orientador: Siebra, Clauirton de Albuquerque Abstract: The rapid expansion of sports betting platforms in Brazil has brought about the prolifera- tion of manipulative design techniques, known as Dark Patterns, which can compromise user autonomy and decision-making. This dissertation proposes a hybrid methodology for the identification and analysis of these practices, integrating Natural Language Processing (NLP) techniques and structural interface inspection. The methodological path involved the investigation of 22 platforms operating in the national market during the period in which the research was conducted. For textual analysis, the BERTimbau model — a Transformer-based architecture fine-tuned for Brazilian Portuguese — was used, achieving a weighted average F1-Score of 0.82 in the classification of categories such as Urgency and Social Proof. Concurrently, the inspection of style sheets (CSS) revealed more than 8,000 occurrences of the opacity:0 property, signaling the presence of potentially hidden or obstructive interface elements. The results show that platforms adapt traditional e-commerce tactics to the betting context, exploring cognitive vulnerabilities through temporal pressure and programmed technical barriers. It is concluded that the sophisti- cation of these strategies, although detectable by automated methods, demands specific regulation regarding interface design in the sector, aiming for consumer protection and the preservation of mental health in the face of predatory business models. Editor: Universidade Federal da Paraíba Tipo: Dissertação Thu, 12 Feb 2026 00:00:00 GMT https://repositorio.ufpb.br/jspui/handle/123456789/38252 2026-02-12T00:00:00Z https://repositorio.ufpb.br/jspui/handle/123456789/38240 Título: Diagnóstico em tempo real de falhas em drones através das análises de sinais de vibração baseadas no caos usando densidade e amplitude de máximos Autor(es): Nunes, Alexandre Magno da Silva Orientador: Brito, Alisson Vasconcelos de Abstract: The Unmanned Aerial Vehicle (UAV) has become popular over the years in various ac- tivities, whether commercial or recreational. However, drones still do not have complete confidence when it comes to safety. Therefore, there is a need to create fault identification techniques that fit the limitations found. This work aims to detect and diagnose drone failu- res in real time and proposes an architecture to identify mechanical failures. The approach proposed in the work uses chaos-based signal analysis techniques using maximum density (SAC-DM) and maximum amplitude (SAC-AM). To achieve the results, data were captured from a quadcopter drone and applied classification techniques and algorithms. With SAC- DM, performances of 91% were achieved and with SAC-AM 100%. It was also possible to validate the system by diagnosing faults in real time. Editor: Universidade Federal da Paraíba Tipo: Dissertação Wed, 31 Aug 2022 00:00:00 GMT https://repositorio.ufpb.br/jspui/handle/123456789/38240 2022-08-31T00:00:00Z https://repositorio.ufpb.br/jspui/handle/123456789/37836 Título: Videoconferência Acessível para Deficientes Auditivos com Avatar de Libras Automático Autor(es): Soares Filho, José Leoberto Orientador: Souza Filho, Guido Lemos de Abstract: Given the increased use of synchronous conferences in the daily activities of the Brazilian population, various adversities have arisen or been exacerbated through this new but already established means of communication. The lack of accessibility for individuals with some form of hearing impairment is one of the most notable challenges, because this portion of society, according to the census conducted by the Brazilian Institute of Geography and Statistics (IBGE) in the year 2010, represented approximately 9.7 million people at that time. There are several laws that ensure access to information for deaf individuals, however, professionals qualified for Portuguese to Brazilian Sign Language (Libras) translation are still a scarce group. With this in mind, this work proposes the incorporation of a Libras Avatar for translating spoken Portuguese language into sign language, while also adding the functionality of automatic captions within the Video For Health (V4H) tool. The results obtained from the proposed experiments showed that the understanding of deaf individuals in videoconferences significantly improved when using the developed tool compared to the platforms available on the internet. Editor: Universidade Federal da Paraíba Tipo: Dissertação Thu, 31 Aug 2023 00:00:00 GMT https://repositorio.ufpb.br/jspui/handle/123456789/37836 2023-08-31T00:00:00Z https://repositorio.ufpb.br/jspui/handle/123456789/37643 Título: Gerenciamento de interseções para otimização do tráfego de carros autônomos Autor(es): Silva, Victor Hugo Azevêdo da Orientador: Siebra, Clauirton de Albuquerque Abstract: Intersections have become, due to the rapid growth of the population of the cities, a prone place for auto accidents and also the main cause of traffic congestion. This work presents a virtual system capable of managing and optimizing the traffic of a region in an environment of autonomous cars. This approach introduces constraints that ensure the safety of stand-alone vehicles, so that they can take advantage of the benefits offered by this new technology without losing confidence. We proposed to remove all traffic lights and signboards present at the intersections, giving the system the responsibility to manage traffic. The results using the SUMO simulator demonstrate that the system was able to optimize vehicle traffic in the various regions used as case studies. Editor: Universidade Federal da Paraíba Tipo: Dissertação Fri, 09 Aug 2019 00:00:00 GMT https://repositorio.ufpb.br/jspui/handle/123456789/37643 2019-08-09T00:00:00Z