The ease of creating digital content coupled with technological advancements allows institutions and organizations to further embrace distance learning. Teaching materials also receive attention, because it is difficult for the student to obtain adequate didactic material, being necessary a high effort and knowledge about the material and the repository. This work presents a framework that enables the automatic metadata generation for materials available in educational video repositories. Each module of the framework works autonomously and can be used in isolation, complemented by another technique or replaced by a more appropriate approach to the field of use, such as repositories with other types of media or other content.
Being able to read fluently directly affects the individual's interaction with society. However, there are few tools that help in the process of developing fluency and in the diagnosis of problems in a playful way. Although applied to foreign language learning, automatic speech recognition (ASR) techniques are not widely used in the literature to support mother tongue development. In this sense, this work proposes a gamified computational approach to diagnose failures in literacy. The proof of concept shows that the tool developed is capable of automatically producing reports that are consistent with reality and useful for teachers and managers in decision-making.
Recommendation systems (RS) have been used in many scenarios, from entertainment to health. Inside the RS area, Educational Recommendation Systems (ERS) are becoming popular, been used for different types of recommendations such as recommending materials, exercises, and learning paths. As ERS works in a different scenario of classics RS, ERS requires specific evaluation metrics. However, the task of evaluating ERS is difficult once the educational field has its features to be analyzed. To help other researchers in this field, this work presents a systematic mapping on methods used for evaluating ERS. This study analyzed 91 papers of the last five years and provide an overview of the main methodologies, subject, metrics, and trends in the evaluation of ERS.
For decision making in government, it is necessary to have well-structured sources of information. In several countries, it is difficult to access government data as the information are dispersed, disconnected, and poorly structured. For this reason, this work presents a framework to gather, unify, and enrich missing person data from distributed web sources. The framework allows inserting new tasks specific to the user’s domain to improve data quality. In this study, Brazilian missing person data from non-governmental organizations (NGOs) and governmental websites were collected and semantically enriched. To enhance the understanding of the gathered missing people cases, we create interpretive models using machine learning techniques to extract knowledge and to encourage the use of standards for publishing the data that are frequently ignored by organizations, hindering analysis and decision-making on data. After the collection and semantic enrichment process, there was an increase of approximately 11% in the data present in the base. Also, the mining process evidenced the disappearance and reappearance of a person in Brazil according to several factors such as age, state initiatives, skin tone, hair colors, etc.
In Brazil, large-scale learning assessment is fundamental for public bodies responsible for education. Through these evaluations, it is possible to plan public policies aimed at improving education. When it comes to the first years of elementary school, an important aspect to evaluate is the ability of the students to use their mother tongue in the oral mode. Nevertheless, the process of evaluating orality on a large scale is still a very costly and time-consuming task. This paper proposes and evaluates the use of Automatic Speech Recognition (ASR) for the automation of this evaluation process. Experiments were performed on a real base of audios and it was demonstrated that the automatic evaluation closely reflects the quality of the analyzed readings.Resumo. No Brasil, a avaliação de aprendizagem em larga escalaé fundamental para osórgãos públicos responsáveis pela educação. Quando se trata dos primeiros anos do ensino fundamental, um importante aspecto a se avaliaré a capacidade do aluno utilizar a sua língua materna na modalidade oral. Apesar disso, o processo de avaliação da fluência em leitura em larga escala aindaé uma tarefa muito dispendiosa em termos financeiros e de tempo. Este trabalho propõe e avalia o uso de reconhecimento automático de fala (ASR) para a automatização desse processo. Experimentos foram realizados em uma base real deáudios e foi demonstrado que a avaliação automática reflete, de forma próxima, a qualidade das leituras analisadas por especialistas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.