This innovative practice full paper focuses on developing a Portuguese-to-Libras translation model designed to facilitate the participation of deaf students in academic conferences in the absence of sign language interpreters. The pursuit of remote solutions, such as virtual translators for simultaneous interpretation from Portuguese to Libras, is intended to facilitate the inclusion of deaf students in higher education during the pandemic, despite the presence of bureaucratic barriers and interpreter shortages. The education of deaf individuals presents a distinctive set of challenges that necessitate the development of innovative technological and methodological approaches to enhance inclusion and promote academic success. Some studies have investigated these issues and put forward proposals for improving the educational experience of deaf individuals. The overarching objective of the research was to apply natural language processing (NLP) techniques, utilizing the Transformer deep learning neural network architecture, to translate Brazilian Portuguese into Libras, thereby facilitating real-time translation and emulating the actions of human interpreters through a virtual character. The specific objectives were to create a dataset comprising Portuguese sentences and their corresponding Libras representations, develop a speech-to-text algorithm, identify and adapt suitable models for translation, and evaluate the performance of translations and the integration of speech-to-text with the NLP model. These objectives were established to ensure accuracy and efficacy in translation and system integration. This research project entailed the construction of an automated translation model from Portuguese to Libras, based on the T5 architecture from Hugging Face. Additionally, a speech recognition system was developed to transcribe audio into text. The translation accuracy, evaluated using the BLEU metric, was 75.32%, which was compared with the glossed sentences in Libras used as the linguistic corpus. However, the model encountered challenges with diacritics and specific vocabulary. The simultaneous interpreter, which combined speech-to-text with the NLP model, demonstrated promising results in real-time translations to Libras.

This full paper describes a complete article in the research category. This work presents a Bibliometric Review that aims to characterize the current scenario of academic research in Artificial Intelligence in education to support educators in the teaching and learning processes in Special Education in different contexts, becoming a tool with potential use in cases of students with Autism Spectrum Disorder (ASD). In this sense, this work aims to contribute to a better understanding of research associated with the area of Artificial Intelligence aimed at educational processes involving students with autism. To do this, we used the EndNote reference manager, an online tool designed to support researchers in conducting Literature Reviews, following the bibliometric protocol proposed by Guedes and Borschiver (2005). From the definition of search strings, (“artificial intelligence”) AND (“autism” OR “ASD” OR “autism spectrum disorder”) AND (“education” OR “teaching”), scientific databases were explored like Web of Science (WoS), Scopus, ERIC, Emerald, Scielo, Portal CAPES, and IEEE, to locate existing studies on the topic, between 2019 and 2024. As a result, 298 articles were mapped and 20 scientific works were selected that address the aforementioned specific theme, written by 89 authors belonging to 50 institutions in 19 countries on four continents, enabling the creation of a significant theoretical basis. By analyzing the information contained in scientific publications in this specific field, it was possible to infer that research is divided into distinct areas of concentration: 1) the exploration of algorithms and data analysis based on Artificial Intelligence for analytical-predictive issues in the field of special education; 2) the use of robots in the teaching and learning processes of students with autism; 3) the development of personalized educational intervention models for learning pedagogical, social and communication skills. The data show that research on the use of Artificial Intelligence in the education of autistic people can still be explored, presenting itself as a promising area for future investigations. The present study facilitates understanding of the current state of knowledge in this area, by identifying gaps in areas that require investigation, thus promoting the development of further research. Finally, the data observed with this research will serve as a basis for the development of future AI projects in the teaching and learning process for autistic students.

This work presents an alternative model to traditional educational recommender systems techniques. The model proposes the description of Learning Objects (LO) and User Profiles as OWL ontology individuals. We propose that the use of ontologies can be very helpful when we seek to accomplish an overall domain interoperability and knowledge description. It is also fundamental for our proposal that a common vocabulary is used. For that, the core of the ontologies are described with the use of the OBAA metadata standard, an extension to IEEE LOM that provides interoperability among hardware platforms for the Brazilian context. Also is part of this work to present a set of practices to develop educational Recommender Systems supported by ontologies.

The development of systems which adapt to the needs of student learning is a complex task. Learning involves several factors, including effective communication in a specific context. In this paper, we propose a conceptual framework to allow the integration of adaptive hypermedia in learning management systems from a cognitive-semantic perspective.

Achieving faithful representation of knowledge is a historic and still unreached goal in the area of Artificial Intelligence. Computational systems that store knowledge in many different ways have been built in order to emulate the capacity of human knowledge representation, taking into consideration the several inherent difficulties to it. Within this context, this paper proposes an experiment that utilizes two distinct ways of representing knowledge: symbolic, BDI in this case, and probabilistic, Bayesian Networks in this case. In order to develop a proof of concept of this proposal for knowledge representation, examples that will be built through agent oriented programming technology will be used. For that, implementation of a MultiAgent system was developed, extending the Jason framework through the implementation of a plug in called COPA. For the representation of probabilistic knowledge, a Bayesian Network building tool, also adapted to this system, was used. The case studies showed improvement in the management of uncertain knowledge in relation to the building approaches of classic BDI agents, i.e., that do not use probabilistic knowledge.

This work presents a recommender system infrastructure for educational material described with metadata. The idea is to provide a set of flexible premises that allows reasoning and improved personalized results in learning content recommendations. For its operation we propose the use of the OBAA standard, which is an extension of IEEE LOM that provides interoperability among hardware platforms contextualized with the Brazilian Educational domain. The technological core of this infrastructure is based on the use of FOAF to describe user profiles, an OWL Ontology to describe specific domain features as well as to facilitate the reasoning process, a Web Service that connects to a federate educational content repository, and a Collaborative Filtering Algorithm as an algorithm recommendation.

This paper presents issues related to an educational portal design and collaboration in intelligent tutoring systems (ITS). In order to achieve the collaboration it was necessary to provide a way to interoperate knowledge among the heterogeneous systems. We have been developing ITS as resources to improve the individual and personalized learning. We believe that individual experiences can be more successful when the student has more autonomy and he is less dependent of the professor. This paper details the social agent, an agent to improve student's learning stimulating his interaction with other students, specially how this agent exchange Bayesian knowledge among AMPLIA agents. The AMPLIA environment is an intelligent probabilistic multi-agent environment to support the diagnostic reasoning development and the diagnostic hypotheses modeling of domains with complex and uncertain knowledge, like medical area.

This work presents an investigation of the use of ChatBots as a tool for network management training, through the use of the problem-based oriented (PBO) approach. Network management can be defined as the act of initializing, monitoring and modifying the operation of the functions that directly support the user requirements. Managing the current heterogeneous networks requires the collection of large quantities of data from the network; data that must then be analyzed before a management activity is initiated. Due to this fact, this domain represents an opportunity for using the PBO approach in education. In our approach, we have created Dorothy, a network management-aware ChatBot that is able to interact not only with the user, but also with the managed network via management protocols.

This work proposes the exploration of student's information through the use of Bayesian Networks. By using this approach we aim to model the uncertainty inherent to the student's behavior. An animated character uses this information to stimulate the imagination and increase student's motivation.

This paper presents a study of a Student Model based on beliefs of Self-Efficacy to improve the effectiveness of Intelligent E-Learning System. The Self-efficacy means the student’s belief on his capacity of performing a task. This belief affects his behavior, motivation, affectivity and the choices he makes. We design an e-Learning System, called InteliWeb, this environment is composed by the Self-Efficacy Mediator Agent, an animated pedagogical agent and offers instruction material on Biological sciences. We use fuzzy theory for dealing with uncertainty in the assessment of the students and the incomplete knowledge about his Self-Efficacy.

Cooperative learning is changing the learning environments design. Intelligent tutoring systems, multi-agent systems, affective computing and virtual characters, are techniques and resources to improve the individual and personalized learning. In this research direction, this paper presents a socio-affective agent whose reasoning is based on individual aspects of the student, as affective states, personality and acceptance, and group aspects, as cohesion. This socio-affective agent is being integrated in the AMPLIA environment, an intelligent probabilistic multi-agent environment to support the diagnostic reasoning development and the diagnostic hypotheses modeling of domains with complex and uncertain knowledge, like medical area. In order to provide semantic interoperability between the environment's agents we are using an OWL (Web Ontology Language)

This article presents InteliWeb, an intelligent e-learning system, which has an agent responsible for promoting the sense of self-efficacy and motivating the student. Self-efficacy means the student's belief on his own capacity of performing a task. This belief affects his behavior, motivation, affectivity and the choices he makes. This environment is composed of the student model manager agent (SMM) and of an animated pedagogical agent and offers instructional material on biological sciences implemented with servlets and JSP pages.