Stéphanie Jean-Daubias

The Ambre ILE: How to Use Case-Based Reasoning to Teach Methods

Designing an Interactive Learning Environment (ILE) requires work within a multi-disciplinary team [9]. In this paper, we describe the designing process of the ILE AMBRE, the purpose of which is to teach methods. We show how, based on didactic work, we chose to represent the expert knowledge to be taught to the learner through Artificial Intelligence techniques. We also describe how we adjusted the Case-Based Reasoning paradigm (CBR), derived from Artificial Intelligence, to teaching abstract knowledge based on problem classes. Last we describe a Cognitive Psychology experiment we conducted in order to test the appropriateness of the thus designed EIAH to the goals of the AMBRE project.

ITS Evaluation in Classroom: The Case of Ambre-AWP

This paper describes the evaluation of an Intelligent Tutoring System (ITS) designed within the framework of the multidisciplinary Ambre project. The aim of this ITS is to teach abstract knowledge based on problem classes thanks to the Case-Based Reasoning paradigm. We present here Ambre-AWP, an ITS we designed following this principle for additive word problems domain and we describe how we evaluated it. We conducted first a pre-experiment with five users. Then we conducted an experiment in classroom with 76 eight-year-old pupils using comparative methods. We present the quantitative results and we discuss them using results of qualitative analysis.

Adding Epiphytic Assistance Systems in Learning Applications Using the SEPIA System

In this paper, we present how the SEPIA system can be used to plug pedagogical and technical assistance systems in applications used by learners in an educational context. The SEPIA system consists in two main tools: an assistance editor that enables assistance designers to specify the assistance they wish for existing applications, and a generic assistance engine that executes the specified assistance in order to provide the application end-users with personalized assistance. We also present an experimentation of an assistance system setup with SEPIA in the context of a bachelor degree.

Towards the Right Assistance at the Right Time for Using Complex Interfaces

Many users struggle when they have to use complex interfaces to complete everyday computing tasks. Offering intelligent, proactive assistance is becoming commonplace yet determining the right time to provide help is still difficult. We conducted an empirical study that aimed to uncover what user factors influenced following advice. Our results describe a users background and expectations that appear to play a role in heeding assistance. Our work is a step towards understanding how to provide the right assistance at the right time and build proactive assistance systems that are personalized for individual users.

aLDEAS: A Language to Define Epiphytic Assistance Systems

We propose a graphical language that enables the specification of assistance systems for a given application, by means of a set of rules. This language is completed by several assistance actions patterns. We implemented these propositions through an assistance editor aimed at assistance designers, and a generic assistance engine able to execute the specified assistance for the target-application end users, without a need to modify this application. We performed several experimentations both with assistance designers and with target-applications end users.

How to combine objectives and methods of evaluation in iterative ILE design: lessons learned from designing Ambre-add

This article deals with evaluating an interactive learning environment (ILE) during the iterative-design process. Various aspects of the system must be assessed and a number of evaluation methods are available. In designing the ILE Ambre-add, several techniques were combined to test and refine the system. In particular, we point out the merits of combining measures of the ILEs impact on learning with analyses of the learners activity. In this article, the approach used to evaluate Ambre-add is described and analyzed, and its advantages and disadvantages are discussed. Then, a general procedure for evaluating ILEs during iterative design is proposed.

Model of Articulation Between Elements of a Pedagogical Assistance

The AGATE project proposed the SEPIA system that allows an assistance designer to define assistance systems added in target applications. In Interactive Learning Environments, such assistance systems are useful to promote the acquisition of knowledge. These assistance systems consist of a set of aLDEAS rules. Our study of assistance in existing applications shows that the articulation between the rules of assistance can take many forms. We propose and implement a model of articulation between assistance rules with the five modes of articulation that we have identified. This model makes explicit and facilitates the definition of articulation between the rules of an assistance system.

Langage et outils pour la spécification et l’exécution d’assistance à l’utilisateur dans des applications existantes

Afin de permettre la specification et l’execution automatique de systemes d’assistance, nous proposons aLDEAS, un langage graphique. Un systeme d’assistance aLDEAS est defini par un ensemble de regles d’assistance respectant un patron de regles. Ce langage est complete par plusieurs patrons qui facilitent la definition d’actions d’assistance complexes frequemment utilisees. aLDEAS est implemente dans le systeme SEPIA, qui consiste principalement en un editeur d’assistance et un moteur generique d’assistance. La plupart des applications existantes peuvent etre surveillees par SEPIA afin de fournir aux utilisateurs finaux une assistance contextualisee et personnalisee. Nous avons realise plusieurs experimentations avec d’une part, des concepteurs d’assistance et, d’autre part, des utilisateurs finaux afin d’evaluer nos propositions.

Adapting the SEPIA system to the educational context

The SEPIA system allows creating assistance systems that meet technical assistance needs. In this paper, we aim at the exploitation of SEPIA in the educational context by confronting it to pedagogical assistance needs. This exploitation shows the limitations in the SEPIA system: complex description of rules by pedagogical designers, lack of domain knowledge. Therefore, we present our patterns that facilitate the creation of assistance systems in the educational context and our ideas to allow the exploitation of domain knowledge.

Une approche unifiée pour proposer des activités interactives entièrement personnalisées sur les profils d’apprenants

Dans le domaine des EIAH (Environnements Informatiques pour l’Apprentissage Humain), la personnalisation de l’enseignement tient un role majeur en raison du fort potentiel de ce paradigme pour l’apprentissage. Par ailleurs, dans le contexte des recherches sur le modele ouvert de l’apprenant, de plus en plus d’EIAH proposent des activites reflexives basees sur la visualisation de profils d’apprenants. Neanmoins, la personnalisation de telles activites reste peu etudiee alors qu’elle pourrait rendre ces activites plus efficaces encore. Nous nous sommes interessees a cette question et avons propose une approche de personnalisation unifiee multi-aspects des activites sur les profils. Nous presentons dans cet article les modeles sur lesquels repose notre approche. Ces modeles permettent la creation de seances d’activites sur les profils, de maniere entierement personnalisee par l’enseignant, tout en prenant en compte les connaissances et competences des apprenants, ainsi que les capacites et preferences de l’ensemble des utilisateurs.