Carine G. Webber

From errors to conceptions: An approach to student diagnosis

A particular challenge in the domain of student diagnosis concerns how to ‘recognize’ and ‘remediate’ student errors. Machine learning techniques have been successfully applied to identify categories of errors and then to discriminate a new error in order to provide feedback to the student. However, remediation very often requires interpreting student errors in terms of knowledge in the context of a specific learning situation. This work is mainly concerned with this problem area. In this sense, we present here an approach to student diagnosis founded on a cognitive framework, called Conception Model, developed in the domain of educational research. The main issue about the Conception Model is the fact that it allows representing student errors in terms of knowledge applied to a learning context. We describe the main aspects of the student diagnosis system we have implemented, and then we evaluate the diagnosis results by comparing them to human diagnoses.

Adding security to a multiagent learning platform

This article discusses security requirements for open distributed learning environments. Security is a critical issue, especially for highly interactive applications based on heterogeneous distributed architectures. In e-learning applications, security mechanisms have as their main purpose to protect against illegal access to information, so that confidentiality and integrity can be guaranteed. While a lot of effort in the e-learning domain has been put into delivering infrastructure and providing content, security issues have hardly ever been considered. Taking this fact into account, we have implemented a multiagent platform (the PMA3), which constitutes an open distributed infrastructure that addresses security issues. PMA3 is founded on multiagent principles and FIPA standards, and has been used in the development of e-learning environments.

Testing Phishing Detection Criteria and Methods

Phishing attacks have increased in the last years despite the use of anti-phishing filters. This is mainly caused by the diversity of phishers trials and the improvement on targeting potential victims on internet. Usually phishers employ social engineering techniques trying to convince users to supply confidential data using the email as the dissemination vehicle. Phishers disguise attacks as trustworthy organizations by cloning websites. According to international monitoring, phishing causes real injury mainly to banks and government institutions. This paper proposes important features to detect phishing attacks employing data mining techniques to evaluate and compare them. In this work we have used public corpora of phishing messages. As a main result we have identified main phishing detection criteria, which have been evaluated and best accurate results were achieved using neural nets and decision trees.

Evaluating automatic group formation mechanisms to promote collaborative learning - a case study

Group work is an important resource that educators have in order to promote collaborative learning situations. In several domains it has been exploited as a valuable teaching strategy. In technical domains, such as logic programming, results on the effect of collaborative activities on learning remains still uncertain. In this sense, this paper intends to contribute with one main research questions: can an automatic group formation mechanism be able to form consistent and successful groups for learning activities? In order to answer this question, we have prepared an experiment with students from computer programming undergraduate course. Students were asked to work individually and in automatically formed pairs. Our conclusion is that group work can help and bring benefits to most learners. We demonstrate in this paper that automatic techniques can produce coherent results regarding group formation.

Ferramenta Especialista para Avaliação de Software Educacional

In the presence of the actual world context, the importance of knowing the technological resources and making use of them to improve the performance of human activities is realized. Educat ion cannot be laid aside of this reality, on the contrary, it has to be allied and seek for resources to improve even more the process of teaching and learn ing through Information and Communication Technologies (ICTs). Thus, the dof Araucaria/PR, through the Educational Technology Project, has pro vided access to these resources establishing informatics laboratories, ev aluating and reorganizing the used method, as an example, the accomplishment of the Leader-Teacher function related to the laboratory monitor one. Resumo. Diante do contexto do mundo atual, percebe-se a imp ortância de conhecer os recursos tecnologicos e fazer uso deste s para melhorar o desempenho das atividades humanas. A educacao nao pficar a margem desta realidade, ao contrario, deve buscar meios de aprimorar o processo de ensino e aprendizagem por meio das Tecnologias da I nformacao e Comunicacao (TICs). Assim, o municipio de Araucari a/PR, atraves do Projeto de Tecnologia Educacional, tem viabilizado o acesso a estes recursos com a implantacao de laboratorios de informatica, ae reorganizando os metodos empregados, como por exemplo, a implemen tacao da funcao de Professor-orientador em detrimento a funcao do moni tor de laboratorio.

UTILIZAÇÃO DE ALGORITMOS DE AGRUPAMENTO NA MINERAÇÃO DE DADOS EDUCACIONAIS

A mineracao de dados educacionais e uma tarefa importante dado o grande volume de informacoes produzidas pelos softwares educacionais. Minerar significa buscar padroes relevantes que possam ser usados para aprimorar os processos de aprendizagem. Este estudo analisa ferramentas de mineracao em tres conjuntos de dados publicos: Geometry, Chinese Tone Study e Algebra I 2006. Os resultados obtidos foram tabulados e analisados atraves dos criterios de homogeneidade e separacao. A analise identificou que as ferramentas sao insuficientes para trabalhar com dados educacionais. Contudo, a ferramenta imunologica foi a que apresentou melhores resultados.

Self and non-self discrimination agents

The goal of this work is to study emergent mechanisms that could possibly be embedded in multiagents systems in order to solve complex problems of distributed diagnosis. We assume the hypothesis that emergent functionalities share important structural and constitutive aspects, independently of the domain from which they emerge. The challenge of understanding self-organizing mechanisms (which allow that emergence occurs in nature) is important to develop systems able to better learn and adapt. Following such perspective we have been studying the human immune system (HIS) as a metaphor to solve problems where complexity and distribution are crucial constraints. Work in this paper reflects how characteristics from the HIS can be applied to conceive diagnosis systems. An application was implemented to student diagnosis in the context of an educational environment for learning basic programming skills.

DESENVOLVENDO JOGOS EDUCACIONAIS POR MEIO DE SOFTWARES DE AUTORIA

Softwares de autoria sao ferramentas para desenvolvimento de aplicacoes multimidia. Elas veem sendo empregadas com sucesso no desenvolvimento de softwares educacionais por serem ferramentas que nao exigem conhecimentos sofisticados em programacao. Contudo a area carece de um estudo avaliativo que permita atestar quais softwares de autoria sao mais apropriados para a criacao de jogos educacionais. Primeiramente este artigo aborda elementos presentes em jogos que possam ser aplicados em projetos educacionais. A partir de um conjunto de criterios este artigo propoe uma analise de softwares de autoria. Os softwares foram testados e avaliados pelo metodo analitico hierarquico. Como resultado o software de autoria melhor avaliado foi o Visual Class.

UnderMine Text Miner – Uma Ferramenta de Mineração de Texto para Área Educacional

Este artigo apresenta um sistema de mineracao de textos, denominado UnderMine Text Miner, que utiliza algoritmos embasados nas metodologias imunologicas. O UnderMine Text Miner opera basicamente dois processos. No primeiro processo de treinamento, o sistema e executado sucessivamente a fim de apreender palavras que contextualizam textos lidos para cada area de estudo informada pelo usuario. No segundo processo de classificacao, o sistema analisa um novo texto e o classifica segundo as areas de estudo aprendidas no primeiro processo. Para finalizar, o artigo descreve experimentos preliminares realizados e exemplos.

Softwares para desenvolvimento de habilidades em Língua Inglesa

Apesar de bem-vista na sociedade, a Lingua Inglesa ainda encontra dificuldades, tratando-se do seu ensino. Os principais problemas sao o aprendizado tardio, falta de contato com o idioma e medo de errar ao se expor, principalmente em relacao as habilidades de listening e speaking. Este trabalho tem como objetivo principal analisar softwares que possam auxiliar no desenvolvimento de habilidades referentes a aprendizagem da Lingua Inglesa. No decorrer do trabalho procurou-se verificar a eficacia da utilizacao destes softwares aplicando-se, inicialmente, um pre-teste com questoes referentes as quatro habilidades (reading, listening, writing e speaking) para verificar o conhecimento previo dos estudantes. Em resposta ao pre-teste, o speaking foi a habilidade que apresentou maior dificuldade, seguida do listening. Logo apos, os estudantes utilizaram os softwares e, por fim, foi realizado um pos-teste, que envolvia as mesmas habilidades testadas anteriormente. A conclusao do trabalho revela que apos a utilizacao dos softwares houve uma melhora significativa nas quatro habilidades em questao. http://dx.doi.org/10.18226/23185279.v5iss2p108