Nathalie Guin

Comparing Student Models in Different Formalisms by Predicting Their Impact on Help Success

We describe a method to evaluate how student models affect ITS decision quality – their raison d’etre. Given logs of randomized tutorial decisions and ensuing student performance, we train a classifier to predict tutor decision outcomes (success or failure) based on situation features, such as student and task. We define a decision policy that selects whichever tutor action the trained classifier predicts in the current situation is likeliest to lead to a successful outcome. The ideal but costly way to evaluate such a policy is to implement it in the tutor and collect new data, which may require months of tutor use by hundreds of students. Instead, we use historical data to simulate a policy by extrapolating its effects from the subset of randomized decisions that happened to follow the policy. We then compare policies based on alternative student models by their simulated impact on the success rate of tutorial decisions. We test the method on data logged by Project LISTEN’s Reading Tutor, which chooses randomly which type of help to give on a word. We report the cross-validated accuracy of predictions based on four types of student models, and compare the resulting policies’ expected success and coverage. The method provides a utility-relevant metric to compare student models expressed in different formalisms.

An Authoring Tool for Semi-automatic Generation of Self-assessment Exercises

In this article we propose a semi-automatic generator of self-assessment exercises. This work is part of the CLAIRE project the aim of which is to design a collaborative authoring platform for pedagogic content. The proposed generator of exercises allows the author (usually a teacher) to create a model of exercise according to his/her pedagogic objectives. This model is automatically instantiated to produce several different exercises that evaluate the same skills. The learner’s answer is automatically and instantly evaluated by the system. He/she thus receives immediate feedback on his/her skills. The distinctive feature of this generator is that the proposed types of exercise are independent of the domain, which allows them to be used for many different subjects and levels. In addition, domain knowledge is used to facilitate the author’s task when the model of exercises and the diagnostic are designed.

A Trace-Based Learner Modelling Framework for Technology-Enhanced Learning Systems

In this paper we present a general framework to describe a trace-based learner modelling process. This framework includes three knowledge models: the first model is an explicit representation of observations about learner’s interactions with a TEL-system, the second model describes the structure and elements describing the Learner Model and the last model describes the main knowledge elements types that could be required to calculate and infer learner profile elements (leaner individual features).

Basing Learner Modelling on an Ontology of Knowledge and Skills

The aim of the research described in this paper is to construct learner skill profiles. The profiles represent the proficiency in knowledge described by an ontology. For this, we identify three needs: a need for a knowledge reference system that organizes knowledge, for identification of the learner knowledge used in the exercises and for a diagnosis model of knowledge. We describe how we propose to respond to each need. In particular, we propose the calculation of three types of mastery values for the knowledge. The diagnosis model we suggest takes these assessments into account in order to make a profile of each learner.

From a Customizable ITS to an Adaptive ITS

The personalization of learning remains a major challenge for research in Intelligent Tutoring Systems (ITS). We report in this article how we used the Adapte tool to make AMBRE-add adaptive. AMBRE-add is an ITS designed to teach a problem solving method. This ITS includes a module that analyzes the learner’s activity traces in order to compute a learner profile. Furthermore a problem generator enables us to specify activities proposed to the student. In order to design an automated process of personalizing activities according to the learner profile, we used the Adapte system. This is a generic system enabling the definition of a personalization strategy and its application to an external ITS. In this article we present how this tool provides real assistance to an ITS designer wishing to make his/her system adaptive.

Adaptable and reusable query patterns for trace-based learner modelling

This paper defines a framework to describe Learner Modelling (LM) process based on interactions traces. This framework includes an RDF-Based representation of knowledge models that can be used by a LM designer. The first model enables the LM designer to describe observations about learners interactions with a TEL-system. The second model enables the LM designer to describe the structure of learners profile. This framework supports also the description of reusable and adaptable SPARQL-based query patterns. These patterns enable the LM designer to calculate and infer learner profile elements for different TEL systems. We define the notion of query pattern and illustrate its application in the context of two TEL systems.

An Authoring Tool to Elicit Knowledge to be Taught without Programming

Knowledge acquisition is a crucial problem for the design of Intelligent Tutoring Systems (ITSs). To overcome this problem, authoring tools have been proposed. Over two dozen of authoring tools have been built since the earliest days of ITS, but each of them focuses on a particular kind of ITSs such as constraint-based tutors or model-tracing tutors. In the context of the AMBRE project, we are interested in ITSs teaching problem-solving methods. Such ITSs enable learners to acquire a specific method in problem-solving. Despite of the variety of existing authoring tools, these tools do not meet our needs either because approach adopted do not match to AMBRE principle or because they do not allow to represent all knowledge needed to design an AMBRE ITS. We propose AMBRE-KB, an authoring tool to help authors to elicit knowledge needed for the design of AMBRE ITSs. This tool supports the acquisition of knowledge to be taught, and the description of problems to be solved. We present the authoring process and illustrate it using French verb conjugation domain. A preliminary evaluation shows that AMBRE-KB is successful in producing domains models but more thorough evaluation is planned.

Towards an Authoring Tool to Acquire Knowledge for ITS Teaching Problem Solving Methods

We propose a process of knowledge acquisition and an authoring tool to assist teachers who are not IT specialist to explicit knowledge needed to design ITS teaching solving problems methods. This paper describes our authoring tool and the type of knowledge to acquire.

Towards a Capitalization of Processes Analyzing Learning Interaction Traces

Analyzing data coming from e-learning environments can produce knowledge and potentially improve pedagogical efficiency. Nevertheless, TEL community faces heterogeneity concerning e-learning traces, analysis processes and tools leading these analyses. Therefore, analysis processes have to be redefined when their implementation context changes: they cannot be reused, shared nor easily improved. There is no capitalization and we consider this drawback as an obstacle for the whole community. In this paper, we propose an independent formalism to describe analysis processes of e-learning interaction traces, in order to capitalize them and avoid these technical dependencies. We discuss both this capitalization and its place and effects in the iterative learning analysis procedure.

Assistance in Building Student Models Using Knowledge Representation and Machine Learning

We propose a method and a first authoring tool to assist the design and implementation of diagnostic techniques. This method is independent from the domain and allows building more than one technique at once. The method is based on knowledge representation and a semi-automatic machine learning algorithm. We tested the method in two domains, surgery and reading English. Techniques built with our method beat the majority class in terms of accuracy.