CE38 - Révolution numérique : rapports au savoir et à la culture

Intelligent Tutoring System for learning by drawing – SKETCH

Intelligent Tutoring System for learning by drawing

Several recent studies have demonstrated that educational activities based on drawing can have positive effects on the learning of scientific concepts. The advent of innovative devices such as pen-based tablets means that new types of scaffolding based on artificial intelligence can now be designed and assessed, including automatic and personalized realtime guidance during the drawing task.

PROJECT OBJECTIVES

The twofold aim of the SKETCH project is to 1) collaboratively design an intelligent tutoring system (ITS) that can analyze learners' actions in real time during the freehand production of a complex scientific drawing on a tablet, and 2) assess and optimize the effects of this system and the feedback it provides on learning. This project will be carried out jointly by two research teams in Rennes (France): the Psychology, Cognition, Behavior & Communication Laboratory (LP3C), and the IntuiDoc team at the Computer Science Laboratory (IRISA). It will focus on drawing activities intended to enhance learning about anatomy. Two of the partners in the project are paramedical colleges: IFPEK and IFPS. This will allow instructors and students to be involved in the project.<br /><br />The ITS will support the drawing activity on the tablet in a variety of ways (visual or verbal support, feedback, demonstrations, contextual aids). In the first phase of the project, the instructor will decide which support to implement (static tutoring). In the second phase, however, the use of artificial intelligence techniques (pattern recognition, knowledge modeling) will allow for the provision of realtime personalized feedback adapted to the difficulties encountered by individual learners (dynamic tutoring).

From a methodological point of view, two complementary approaches are implemented: user-centered design, and experimental methodology. The first approach means that the different end-users (students and instructors) are involved in the development of the system, so that it is tailored to their needs and is easy to use. The experimental methodology is used in parallel to validate the different functionalities of the system as rigorously as possible, comparing the performances and levels of motivation of different groups of students exposed to different versions of the ITS.

LP3C: During an initial needs analysis phase, several actions (interviews and user tests) were carried out with instructors and students from the project's partner institutes. These instructors were then involved in the construction of the teaching materials on the tablet, as well as in the organization of the studies integrated into their courses. Questionnaires identifying students' drawing-based learning strategies were also distributed in various medical and paramedical fields. A study to evaluate the user experience with the tool was carried out with psychology students. The results showed a high level of acceptability and situational interest.
Three larger-scale experimental studies were carried out as part of the psychology thesis. Their aim was to evaluate the effects of drawing on the quality of learning. The first study involved 90 first-year physiotherapy students. The other studies involved a class of 97 second-year nursing students. The results showed 1) high scores of perceived usefulness of the drawing activity, and 2) a beneficial effect on short- and long-term memorization of spatial and pictorial information.
IRISA: The first phase consisted in developing a static ITS (WP2.1). Feedback from user tests led to the evolution of the static ITS, and significant progress was made on the dynamic ITS, mainly on the authoring mode enabling the teacher to create new exercises (WP2.3). As supervised rule extraction was not addressed in this phase, our work focused on the student mode (WP2.4).
We implemented pattern recognition techniques based on two-dimensional grammatical composition rules to model document structure and enrich domain knowledge. To model the system's tutorial knowledge, we rely on domain constraint-based modeling, i.e. a problem is represented by a set of constraints that must be satisfied for the exercise to be solved. These constraints are represented by a knowledge graph.
We have implemented a first dynamic ITS version («IntuiSketch«) in student mode, which analyzes students' handwritten tracings relative to an exercise given as input (drawing of the anatomy of the lumbar spine). The system is able to analyze the student's tracings and generate feedback on the shape, location and spatial constraints linking the various anatomical entities.

The project's research work will continue with the development of dynamic ITS and the implementation of studies on the effects of different forms of guidance offered by instructors or ITS.

Barchouch I., Anquetil E., Girard N., Krichen O. Système tutoriel intelligent pour l'apprentissage par croquis Projet Sketch. SIFED 2023 – Symposium International Francophone sur l’Ecrit et le Document, Jun 2023, Paris, France.

Recent work shown that pedagogical activities based on sketching have positive effects on the quality of learning of scientific concepts, especially when the learner is guided in this activity. If the activity is carried out on a pen-based tablet, then innovative guidance based on artificial intelligence can be designed. This project will focus on sketching within the framework of learning in anatomy. Its objective will be to design an intelligent tutoring system that is capable of analyzing in real time the actions of the learner during the freehand elaboration of a complex scientific sketch. By comparing these sketches to the teacher's model, this system will be able to provide real-time guidance and feedback to learners. In order to optimize their effects on learning, these supports will be evaluated in a series of studies involving several hundred paramedical training students.

Project coordination

Eric Jamet (Laboratoire de Psychologie : Cognition, Comportement, Communication)

The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.

Partner

IRISA Institut de Recherche en Informatique et Systèmes Aléatoires
LP3C Laboratoire de Psychologie : Cognition, Comportement, Communication

Help of the ANR 484,623 euros
Beginning and duration of the scientific project: - 42 Months

Useful links

Explorez notre base de projets financés

 

 

ANR makes available its datasets on funded projects, click here to find more.

Sign up for the latest news:
Subscribe to our newsletter