Search

The LEA’s Box open learner model (OLM) allows learners to try to persuade the system to make changes to their learner model by challenging evidence or providing learning-based justifications. This aims to help make the OLM more accurate, and to support learner reflection, planning and self-monitoring. We re-port an evaluation with 15 university students using the OLM to give formative competency information with learner model evidence data coming from online quizzes and teacher assessments. Results show that students generally understand this approach of persuasion, how it is useful, how it relates to their learning, and identified cases when they could use OLM persuasion within their learning.

International audience; The AGATE project proposed the SEPIA system that allows an assistance designer to define assistance systems added in target application. In Interac-tive Learning Environments, such assistance systems are useful to promote the acquisition of knowledge. These assistance systems consist of a set of aLDEAS rules. The articulation between these rules was expressed until now implicitly in the aLDEAS language. Our study of assistance in existing appli-cations shows that the articulation between the rules of assistance can take many forms. We propose in this paper firstly a model of articulation between assistance rules with the five modes of articulation that we have identified. We also present our implementation of this model in the SEPIA system. This model makes explicit and facilitates the definition of articulation between the rules of an assistance system

R. Vatrapu, M. D. Kickmeier-Rust, B. Ginon, & S. Bull (Eds.). (2016). Proceedings of the Fourth International Workshop on Teaching Analytics, in conjunction with EC-TEL 2016. September 16, 2016, Lyon, France, S. 23-29

International audience; 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. Thus, we present our patterns that facilitate the creation of assistance systems in the educational context and our ideas to allow exploitation of domain knowledge

International audience; We propose a technique to collect use traces in any existing applica-tion, without a need to modify this application. This technique is based on the use of accessibility libraries. We implemented our technique in a collector that uses UIAutomation and JavaAccessibility libraries: it can monitor Windows target-applications to collect the user’s traces. The traces are then stored in a trace-base management system in order to be exploited thereafter. We have tested our collector on more than fifty applications in order to evaluate our ap-proach.

We propose a technique to collect use traces in any existing applica-tion, without a need to modify this application. This technique is based on the use of accessibility libraries. We implemented our technique in a collector that uses UIAutomation and JavaAccessibility libraries: it can monitor Windows target-applications to collect the user’s traces. The traces are then stored in a trace-base management system in order to be exploited thereafter. We have tested our collector on more than fifty applications in order to evaluate our ap-proach.

International audience; In this paper, we present our approach to personalize existing and various animated agents, taking into account the context and the users’ knowledge, abilities and preferences. For this purpose, we propose a grammar to describe animated agents in a common formalism, and specify their characteristics and abilities. According to this description, it is then possible to define actions with parameters that can be used and personalized in a description of the required assistance for a given application, which is used by a generic assistant to provide each user with personalized assistance.

International audience; In research on the open learner model, more and more ILE offer to learners interactive activities on their profile. These activities are based on the visualization of learners profiles: in particular, it may be a simple observation of a profile, but also the negotiation of this profile content, or a comparison with another learner profile. However, the visualization of profiles proposed by existing ILE is few customizable. In this paper, we present models to personalize activities on profiles, depending on the user type (learner, teacher...), on his knowledge, skills and capacities, but also on his preferences. We implemented these models to provide tools to teachers to prepare personalized activities on profiles; and to provide to each user type a unified environment proposing personalized activities on profiles.