文章基本信息

标题：Sequenciamento Adaptivo de Exercícios baseado na Correspondência entre a Dificuldade da Solução e o Desempenho Dinâmico do Aprendiz
本地全文：下载
作者：Rômulo Silva ; Alexandre Direne
期刊名称：Anais dos Workshops do Congresso Brasileiro de Informática na Educação
印刷版ISSN：2316-8889
出版年度：2016
卷号：5
期号：1
页码：11
DOI：10.5753/cbie.wcbie.2016.11
语种：Portuguese
出版社：Anais dos Workshops do Congresso Brasileiro de Informática na Educação
摘要：The expertise of learners is usually developed by solving problems that require a set of assessed skills. This is done in both conventional education schools and by applying advanced learning technologies, such as Intelligent Tutoring Systems. This research proposed a formula for automatic assessment of students, assuming that the degree of difficulty of the questions can be measured by counting the students that are successful and those who failed. This information is used to calculate their grade as a particular rating scale. Besides, the motivational aspects of learning are considered in depth. In this sense, it is important to propose activities according to the student's level of expertise, which is achieved through presenting students with exercises that are compatible with the difficulty degree of their cognitive skills. In doing so, both boredom and frustation can be avoided, as much as can be the withdrawal of the proposed activities on the part of students. An empirical study based on existing students data partially influenced the development of the first version of an adaptive algorithm for exercises sequencing, based on the difficulty degree of the questions. The sequencing process is guided by the learner's dynamic performance. An experiment has also been carried out with four maths classes of a local public school. Data collected from students' performance gains demonstrated the suitability of the rating formula. The algorithms for calculating and matching the difficulty degree of the questions and the students' rating were implemented by extending the web authoring tool of learning objects named FARMA, thus generating the ADAPTFARMA environment. Finally, conclusions and future research directions are described.