https://repositorio.uema.br/jspui/handle/123456789/1915 2026-08-18T20:20:45Z https://repositorio.uema.br/jspui/handle/123456789/6441 Título: Segmentação de textos jurídicos: estudo de caso em petições Abstact: The growing volume of legal cases highlighted in the 2023 report of the Conselho Nacional de Justiça highlights the urgency of effective strategies for screening and document analysis. With 81.4 million cases pending at the end of 2022, the Judiciary faced a major challenge in terms of management and decision-making regarding this vast set of documents. These documents, mostly textual, can be seen as a sequence of semantically coherent segments, designed to facilitate the transition between different subtopics within a single document. In this way, dividing a document into similar segments can help improve and/or speed up downstream applications. In this sense, the segmentation of initial petitions into descriptions named fact, thesis and request (FTP) emerges as a promising approach. Therefore, this study proposes the construction of an initial petition segmenter, using neural networks together with incorporations from the Bidirection Encoder Representations from Transformers model in a database of petitions to be annotated manually, discovered by Cross Industry Standard Process for Data Mining methodology. The objective lies in performing automated identification of the FTP triplet in order to provide the most relevant parts of the petition in the legal context. Furthermore, the proposed approach can be adapted to other natural language processing tasks, such as summarization and textual search. By focusing on the essential elements for analysis and response, it is expected to reduce the volume of information to be processed, thus optimizing operational efficiency. Furthermore, the division of the petition in particular facilitates the quick and accurate identification of key elements, accelerating the understanding process, especially when sent in conjunction with automated systems and solutions from the Justice 4.0 program 2026-03-28T00:00:00Z https://repositorio.uema.br/jspui/handle/123456789/6353 Título: Acessibilidade Urbana facilitada por um protótipo de sistema para PcD Abstact: This work shows results from the development of a prototype system with a focus on urban accessibility that serves various types of People with Disabilities (PwD), in addition, an academic research questionnaire was applied aiming to amplify the vision regarding the main topic addressed, as well how to evaluate the use of the proposed system solution. The objective of this research is to contribute to society through social inclusion and applicability of the future solution in smart cities, starting through the experiment on an academic campus. This article also delves into technological and social aspects that can serve as a reference for consultations by researchers, public and private bodies who seek depth in their studies. However, as the topic is of great relevance, it is clear that this line of research is still little explored, especially in Brazil, given the limited number of articles available. 2024-01-01T00:00:00Z https://repositorio.uema.br/jspui/handle/123456789/6343 Título: Análise da robótica educacional como instrumento pedagógico no desenvolvimento escolar do ensino fundamental da rede pública Abstact: The present research deals with the analysis of educational robotics as a pedagogical tool in the school development of 5th-grade students in the public school system of Santa Rita-MA. It concerns a study project on the combination of educational robotics and its contribution to Mathematical Logical thinking allied with technology in the early grades of elementary education. Its objectives are to compare traditional methods of teaching mathematics with active methodologies that use educational robotics; stimulate students' interest in the proposal; analyze the problem-solving ability of the presented problems; evaluate students' cognitive development focused on enhanced mathematics learning with the support of robotics kits, and identify which Computational Thinking skills (pattern recognition, decomposition, algorithms, and abstraction) are related to mathematical logic. The investigation has a practical and exploratory nature, with a qualitative and quantitative approach, of an applied nature, using procedures such as case studies and action research, through the conduct of classes, workshops, and the application of evaluative questionnaires in the initial and final phases of the research. Based on the results and findings, it was observed through the case study that educational robotics not only stimulates and interests children in mathematics but also significantly improves academic performance in that area of knowledge. However, it was not possible to effectively compare traditional methods of teaching mathematics with active methodologies that use educational robotics. Therefore, the research concludes that educational robotics, although it promotes various benefits as a practical teaching methodology, requires resources such as collaborative work, a multidisciplinary team, and adequate funding to have effective relevance 2024-01-01T00:00:00Z https://repositorio.uema.br/jspui/handle/123456789/6316 Título: Alucinações em modelos de IA Generativa: limitações e desafios na compreensão da linguagem humana Abstact: Chatbots are artificial intelligence systems that simulate human interactions and have been widely used in diverse areas, from customer service to content creation. However, despite advances in technology, chatbots still present limitations and challenges, such as the tendency to make mistakes and the difficulty in dealing with complex questions and nuances of human language. These errors are known as hallucinations and can be caused by several factors, such as a lack of common sense, biased data and limitations in the models' ability to deal with non-existent or unrepresented information in the data. Chatbot hallucinations can have significant impacts in several areas, such as education, customer service and content creation. For example, a chatbot that cannot understand the nuances of human language may provide inappropriate or incorrect responses, which can lead to a negative user experience. Additionally, chatbots can perpetuate social bias and discrimination if they are trained on biased data. To deal with these limitations in the educational context, it was proposed the development of a chatbot for teaching programming in Python that uses advanced natural language processing techniques to reduce hallucinations when learning the language. 2024-05-31T00:00:00Z