Catálogo de publicaciones - libros

This paper addresses the challenge of providing users with personalized learning resources by gathering and sharing attention information. Starting from our previous works related to the tracking of learning objects’ exploitation within learning systems, we suggest here an extension of this framework based on the Attention.XML standard to offer the opportunity to share attention information between various and heterogeneous applications. An Attention.XML service based on web technologies has been elaborated and integrated within the existing architecture, thus offering standardization and availability to the global environment. This approach makes it easy to integrate existing learning environments and tools, and thus facilitates the generation of attention data specific to these applications.

Engagement is an important aspect of effective learning. Time spent using an e-Learning system is not quality time if the learner is not engaged. Tracking the student disengagement would give the possibility to intervene for motivating the learner at appropriate time. In previous research we showed the possibility to predict engagement from log files using a web-based e-Learning system. In this paper we present the results obtained from another web-based system and compare them to the previous ones. The similarity of results across systems demonstrates that our approach is system-independent and that engagement can be elicited from basic information logged by most e-Learning systems: number of pages read, time spent reading pages, number of tests/ quizzes and time spent on test/ quizzes.

Nowadays, people are in need for continuous learning in order to keep up to date or be upgraded in their job. An infrastructure for lifelong learning requires continuous adaptation to learners needs and must also provide flexible ways for students to use and personalize them. Controlling who can access a document, specifying when a student may be contacted for interactive instant messaging or periodical reminders in order to increase motivation for collaboration are just some examples of typical statements that may be specified by e.g., learners and learning management system administrators. This paper shows how policies can represent a way of expressing these statements and describes the extra benefits of its adoption like flexibility, dynamicity and interoperability.

When a trainer aims to provide trainees with appropriate help and assistance, she/he needs to know what errors the trainee is making and furthermore what causes lead to these errors. In this paper, we propose a mechanism which infers the underlying causes that lead to the production of the trainee’s erroneous action in order to support the trainer in her/his monitoring activity. This mechanism is based on and uses CREAM, a second-generation method of Human Reliability Analysis (HRA). We implement this mechanism by using Dempster-Shafer’s theory.

Indicators help actors to organise, orientate, and navigate through environments by providing contextual information that is relevant for performing learning tasks. In this article we analyse the requirements, present a model and an initial prototype of a software system that uses smart indicators to support learners to be more engaged into the learning process. We argue that indicators need adaptation as learners develop on their learning paths in order to support interactions throughout the learning process. The learning interaction cycle of Garries, Ahlers and Driskel is used as a model for developing an architecture that supports the interaction between a learner and a learning environment. The technical feasibility of the architecture has been tested by implementing that is critically reflected on technical and educational concepts. This article concludes with an outlook on our future research, in which the model will be evaluated by applying the prototype in a learning community.

Currently, large amounts of research exist into the design and implementation of adaptive systems. The complex task of authoring of such systems, or their evaluation, is addressed less. We have looked into the causes of this complexity. Manual annotation is a serious bottleneck for authoring of adaptive hypermedia. All means for supporting this authoring process by reusing automatically generated metadata would therefore be helpful. Previously, we proposed the integration of a generic Adaptive Hypermedia authoring environment, MOT, into a semantic desktop environment, indexed by Beagle++. Based upon this approach, a prototype was constructed. The approach in general, as well as the prototype in particular, where evaluated through both qualitative and quantitative experiments. This paper is a synthesis of our work so far, describing theoretical findings and hypotheses, their implementation in short, and finally, the combined results of the evaluations.

The IMS Learning Design (IMS LD) specification offers a language for modeling teaching and learning situations and flows. The specification contains great complexity, which represents a high entrance barrier to its use. To lower this entrance barrier to Learning Design, easy-to-handle software is needed that translates from the language used by instructional practitioners to IMS LD. This paper describes an approach for performing this translation. First, an analysis is described that was used for deriving typical uses of IMS LD Level B properties and conditions. Second, the resulting cases and translation transactions are presented. It is hypothesized that a wizard allows practitioners access to Level B functionalities even though the wizard reduces the complexity of the specification.

In classrooms teachers know how to motivate their students and exploit this knowledge to adapt or optimize their instruction when a student shows signs of demotivation. In on-line learning environments it is much more difficult to assess the motivation of the student and to have adaptive intervention strategies and rules of application to help prevent attrition. We developed MotSaRT – a motivational strategies recommender tool – to support on-line teachers in motivating learners. The design is informed by Social Cognitive Theory and a survey on motivation intervention strategies carried out with sixty on-line teachers. The survey results were analysed using a data mining algorithm (J48 decision trees) which resulted in a set of decision rules for recommending motivational strategies. MotSaRT has been developed based on these decision rules. Its functionality enables the teacher to specify the learner’s motivation profile. MotSaRT then recommends the most likely intervention strategies to increase motivation.

The paper presents LOCO-Analyst, an educational tool for providing teachers with feedback on the relevant aspects of the learning process taking place in a web-based learning environment. The feedback provision is based on the learning context, which we dubbed Learning Object Context and consider as a complex interplay of learning activities, learning objects, and learners. Here we present a usage scenario based on the real data obtained from the Web-based iHelp Courses Learning Content Management System, in order to illustrate some of the functionalities that LOCO-Analyst provides. We also briefly overview Semantic Web technologies that lay beneath LOCO-Analyst and make it a generic feedback provision tool. Related work is presented as well. The paper concludes with a sketch of our current and planned future efforts for further improving LOCO-Analyst.

Arguing that a varying level of formality needs to be offered in systems supporting collaborative learning, this paper proposes an incremental formalization approach that has been adopted in the development of CoPe_it!, a web-based tool that complies with collaborative principles and practices to provide members of communities with the appropriate means to manage individual and collective knowledge, and collaborate towards the solution of diverse issues. According to the proposed approach, incremental formalization can be achieved through the consideration of alternative projections of a collaborative workspace, as well as through mechanisms supporting the switching from one projection to another. Related features and functionalities are presented through an illustrative example.