Catálogo de publicaciones - libros

This paper presents an approach for intelligent tutoring in the field of legal argumentation. In this approach, students study transcripts of US Supreme Court oral argument and create a graphical representation of argument flow as tests offered by attorneys being challenged by hypotheticals posed by Justices. The proposed system, which is based on the collaborative modeling framework Cool Modes, is capable of detecting three types of weaknesses in arguments; when it does, it presents the student with a self explanation prompt. This kind of feedback seems more appropriate than the “strong connective feedback” typically offered by model-tracing or constraint-based tutors. Structural and context weaknesses in arguments are handled by graph grammars, and the critical problem of detecting and dealing with content weaknesses in student contributions is addressed through a collaborative filtering approach, thereby avoiding the critical problem of natural language processing in legal argumentation. An early version of the system was pilot tested with two students.

During the training phase in an Intelligent Tutoring System, learners usually require help. However, it may happen that the tutor cannot provide such help, unless it has access to additional pedagogical resources. Moreover, in a collaborative but competitive learning environment in which each user could be both learner and expert, security problems may arise. For instance, the exchanges between users could require security services such as anonymity, confidentiality and integrity. In this paper, we introduce a system, called , whose aim is to provide the tutor with mechanisms to capture, exploit, organize, deliver and evaluate learners knowledge, in a secure way, based on the learner-expert concept. Our main contribution is the introduction of security services in an ITS for the benefit of learners. This may be helpful to protect learners’ privacy as well as communication contents and pedagogical resources in an artificial competitive peer environment, thus allowing the tutor to better evaluate learners.

Web-based applications with very diverse learners fail because they fail to satisfy various needs. Some people use collaborative filtering methods to analyze learners’ profiles and provide recommendation to a new learners, but this methods provides false recommendations from beginners. We present a new method, which provides recommendations that depend on the credibility rather than the number of learners. We have designed, implemented, and tested what we call the Intelligent E-Course Agent (IECA). Our evaluation experiment shows that our approach greatly improves learners’ knowledge and therefore presents a course that is more closely related to their needs.

In the field of e-learning, a popular solution to make teaching material reusable is to represent it as learning object (LO). However, building better adaptive educational software also takes an explicit model of the learner’s cognitive process related to LOs. This paper presents a three layers model that explicitly connect the description of learners’ cognitive processes to LOs. The first layer describes the knowledge from a logical perspective. The second describes cognitive processes. The third builds LOs upon the two first layers. The proposed model has been successfully implemented in an intelligent tutoring system for teaching Boolean reduction that provides highly tailored instruction thanks to the model.

This paper presents SEDHI – an adaptive hypermedia system for a web-based distance course. The system architecture includes three main modules: the Classification Module, the Student Module, and the Adaptation Module. SEDHI classifies the students according to profiles that were defined based on a statistical study of the course user and usage data, and adapts the navigation using the techniques of link hiding and link annotation. The results of an evaluation of the SEDHI prototype show the potential of the classification and adaptation approach.

The development of Intelligent Tutoring Systems (ITS) and eLearning systems has been progressing largely independently over the past several years. Both types of systems have strengths and weaknesses – ITSs are typically domain specific and rely on concise knowledge modeling and learner modeling, while eLearning systems are deployable in a wide range of circumstances and focus on connecting learners both to content and to one another. This paper provides possibilities for convergence of these two areas, and describes two of our experiences in providing an ITS-style approach to eLearning systems.

Intelligent Tutoring Systems (ITSs) are usually based on similar fundamental structures. In contrast to this, software engineering techniques are seldomly used for realizing ITSs. In the last years, some approaches tried to change this: pattern mining took place; methods covering the specifics of ITS project development have been deployed. These approaches usually focus on a specific system type or on a certain application domain. What is missing is a combination of all the different approaches in a pattern language or a pattern catalogue for ITS. The purpose of such a pattern catalogue is to provide pattern for different types of software and to support the software development starting from design and ending with the implementation. The first step towards a pattern language is described in this paper.

This paper describes an approach to promote interoperability among heterogeneous agents that are part of an Educational Portal (PortEdu). We focus on a specific agent, the social agent, adding all the necessary functionality for him to interact with agents that aren’t fully aware of its context. The social agent belongs to a Multi-agent Learning Environment designed to support training of diagnostic reasoning and modeling of domains with complex and uncertain knowledge, AMPLIA. The knowledge of the social agent is implemented with Bayesian networks, which allows the agent to represent its probabilistic knowledge and make its decisions. However, to communicate with agents outside AMPLIA, it is necessary to express such probabilistic knowledge in a way that all agents may process. Such requirement is addressed using OWL, an ontology language developed by W3C to be used on the Semantic Web.

Previous studies have demonstrated the learning benefit of personalized language and worked examples. However, previous investigators have primarily been interested in how these interventions support students as they problem solve with cognitive support. We hypothesized that personalized language added to a web-based intelligent tutor and worked examples provided as complements to the tutor would improve student (e-)learning. However, in a 2 x 2 factorial study, we found that personalization and worked examples had no significant effects on learning. On the other hand, there was a significant difference between the pretest and posttest across all conditions, suggesting that the online intelligent tutor present in all conditions make a difference in learning. We conjecture why personalization and, especially, the worked examples did not have the hypothesized effect in this preliminary experiment, and discuss a new study we have begun to further investigate these effects.

When a tutoring system aims to provide learners with accurate and appropriate help and assistance, it needs to know what goals the learner is currently trying to achieve, what plans he is implementing and what errors he is making. That is, it must do both plan recognition and error detection. In this paper, we propose a generic framework which supports two main issues (i) the detection of learner’s unexpected behavior by using the Hollnagel classification of erroneous actions and (ii) a recognition process based on a task model METISSE that we propose. This model, which is used to describe the tasks the learner has to do according to pedagogical goals, allows learner’s unexpected behavior to be detected. The solutions proposed are generic because not dependent on the domain task, and they do not relate to a particular device.