Project-Team Flowers
Team, Visitors, External Collaborators
Overall Objectives
Research Program
Application Domains
Highlights of the Year
New Software and Platforms
New Results
Bilateral Contracts and Grants with Industry
Partnerships and Cooperations
Dissemination
Bibliography
XML PDF e-pub
PDF e-Pub

previous Previous | up Home | Next next

Section: New Results

Applications in Educational Technologies

Machine Learning for Adaptive Personalization in Intelligent Tutoring Systems

Participants : Pierre-Yves Oudeyer [correspondant] , Benjamin Clément, Didier Roy, Helene Sauzeon.
The Kidlearn project

Kidlearn is a research project studying how machine learning can be applied to intelligent tutoring systems. It aims at developing methodologies and software which adaptively personalize sequences of learning activities to the particularities of each individual student. Our systems aim at proposing to the student the right activity at the right time, maximizing concurrently his learning progress and its motivation. In addition to contributing to the efficiency of learning and motivation, the approach is also made to reduce the time needed to design ITS systems.

We continued to develop an approach to Intelligent Tutoring Systems which adaptively personalizes sequences of learning activities to maximize skills acquired by students, taking into account the limited time and motivational resources. At a given point in time, the system proposes to the students the activity which makes them progress faster. We introduced two algorithms that rely on the empirical estimation of the learning progress, RiARiT that uses information about the difficulty of each exercise and ZPDES that uses much less knowledge about the problem.

The system is based on the combination of three approaches. First, it leverages recent models of intrinsically motivated learning by transposing them to active teaching, relying on empirical estimation of learning progress provided by specific activities to particular students. Second, it uses state-of-the-art Multi-Arm Bandit (MAB) techniques to efficiently manage the exploration/exploitation challenge of this optimization process. Third, it leverages expert knowledge to constrain and bootstrap initial exploration of the MAB, while requiring only coarse guidance information of the expert and allowing the system to deal with didactic gaps in its knowledge. The system was evaluated in several large-scale experiments relying on a scenario where 7-8 year old schoolchildren learn how to decompose numbers while manipulating money [68]. Systematic experiments were also presented with simulated students.

Kidlearn Experiments 2018-2019: Evaluating the impact of ZPDES and choice on learning efficiency and motivation

An experiment was held between mars 2018 and July 2019 in order to test the Kidlearn framework in classrooms in Bordeaux Metropole. 600 students from Bordeaux Metropole participated in the experiment. This study had several goals. The first goal was to evaluate the impact of the Kidlearn framework on motivation and learning compared to an Expert Sequence without machine learning. The second goal was to observe the impact of using learning progress to select exercise types within the ZPDES algorithm compared to a random policy. The third goal was to observe the impact of combining ZPDES with the ability to let children make different kinds of choices during the use of the ITS. The last goal was to use the psychological and contextual data measures to see if correlation can be observed between the students psychological state evolution, their profile, their motivation and their learning. The different observations showed that generally, algorithms based on ZPDES provided a better learning experience than an expert sequence. In particular, they provide a better motivating and enriching experience to self-determined students. Details of these new results, as well as the overall results of this project, are presented in Benjamin Clément PhD thesis [69] and are currently being processed to be published.

Kidlearn and Adaptiv'Math

The algorithms developed during the Kidlearn project and Benjamin Clement thesis [69] are being used in an innovation partnership for the development of a pedagogical assistant based on artificial intelligence intended for teachers and students of cycle 2. The algorithms are being written in typescript for the need of the project. The expertise of the team in creating the pedagogical graph and defining the graph parameters used for the algorithms is also a crucial part of the role of the team for the project. One of the main goal of the team here is to transfer technologies developed in the team in a project with the perspective of industrial scaling and see the impact and the feasibility of such scaling.

Kidlearn for numeracy skills with individuals with autism spectrum disorders

Few digital interventions targeting numeracy skills have been evaluated with individuals with autism spectrum disorder (ASD) [114]. Yet, some children and adolescents with ASD have learning difficulties and/or a significant academic delay in mathematics. While ITS are successfully developed for typically developed students to personnalize learning curriculum and then to foster the motivation-learning coupling, they are not or fewly proposed today to student with specific needs. The objective of this pilot study is to test the feasibility of a digital intervention using an STI with high school students with ASD and/or intellectual disability. This application (KidLearn) provides calculation training through currency exchange activities, with a dynamic exercise sequence selection algorithm (ZPDES). 24 students with ASD and/or DI enrolled in specialized classrooms were recruited and divided into two groups: 14 students used the KidLearn application, and 10 students received a control application. Pre-post evaluations show that students using KidLearn improved their calaculation performance, and had a higher level of motivation at the end of the intervention than the control group. These results encourage the use of an STI with students with specific needs to teach numeracy skills, , but need to be replicated on a larger scale. Suggestions for adjusting the interface and teaching method are suggested to improve the impact of the application on students with autism. (Paper is in progress).

Curiosity-driven interaction systems for education

Participants : Pierre-Yves Oudeyer, Hélène Sauzéon [correspondant] , Mehdi Alami, Didier Roy, Edith Law.

Three studies have been developed and conducted to newly design curiosity-driven interaction systems aiming to foster learning performance across lifespan : the first two studies include children and the last one includes the older adults.

The first study regards a new interactive robotic system to foster curiosity-driven learning. This led to an article in CHI 2019 [29]. In this work, we explored whether a social peer robot’s verbal expression of curiosity can be perceived by participants, produce emotional or behavioural contagion effects, and impact learning. In a between-subject experiment involving 30 participants, a peer robot was manipulated to verbally express: curiosity, curiosity plus rationale, or no curiosity (neutral), within the context of LinkedIt!, a cooperative game we designed for teaching students how to classify rocks. Results show that participants were able to reliably recognize curiosity in the robot and curious robots can be used to elicit significantly more curiosity-driven behaviours among participants.

The second study regards a new interactive educational application to foster curiosity-driven question-asking in children. This study has been performed during the Master 2 internship of Mehdi Alaimi co-supervised by H. Sauzéon, E. Law and PY Oudeyer. The paper submission to CHI'20 is just accepted in december 2019 (« Pedagogical Agents for Fostering Question-Asking Skills in Children »). It addresses a key challenge for 21st-century schools, i.e., teaching diverse students with varied abilities and motivations for learning, such as curiosity within educational settings. Among variables eliciting curiosity state, one is known as « knowledge gap », which is a motor for curiosity-driven exploration and learning. It leads to question-asking which is an important factor in the curiosity process and the construction of academic knowledge. However, children questions in classroom are not really frequent and don’t really necessitate deep reasoning. Determined to improve children’s curiosity, we developed a digital application aiming to foster curiosity-related question-asking from texts and their perception of curiosity. To assess its efficiency, we conducted a study with 95 fifth grade students of Bordeaux elementary schools. Two types of interventions were designed, one trying to focus children on the construction of low-level question (i.e. convergent) and one focusing them on high-level questions (i.e. divergent) with the help of prompts or questions starters models. We observed that both interventions increased the number of divergent questions, the question fluency performance, while they did not significantly improve the curiosity perception despite high intrinsic motivation scores they have elicited in children. The curiosity-trait score positively impacted the divergent question score under divergent condition, but not under convergent condition. The overall results supported the efficiency and usefulness of digital applications for fostering children’s curiosity that we need to explore further.

Finaly, the third study investigates the role of intrinsic motivation in spatial learning in late adulthood [25]. We investigated age differences in memory for spatial routes that were either actively (i.e., intinsic motivation condition) or passively (i.e., control condition) encoded. A series of virtual environments were created and presented to 20 younger (Mean age = 19.71) and 20 older (Mean age = 74.55) adults, through a cardboard viewer. During encoding, participants explored routes presented within city, park, and mall virtual environments, and were later asked to re-trace their travelled routes. Critically, participants encoded half the virtual environments by passively viewing a guided tour along a pre-selected route, and half through active exploration with volitional control of their movements by using a button press on the viewer. During retrieval, participants were placed in the same starting location and asked to retrace the previously traveled route. We calculated the percentage overlap in the paths travelled at encoding and retrieval, as an indicator of spatial memory accuracy, and examined various measures indexing individual differences in their cognitive approach and visuo-spatial processing abilities. Results showed that active navigation, compared to passive viewing during encoding, resulted in a higher accuracy in spatial memory, with the magnitude of this memory enhancement being significantly larger in older than in younger adults. Results suggest that age-related deficits in spatial memory can be reduced by active encoding. In other words, this means that conditions where intrinsic motivation is involved, reduce negative effects of aging on spatial learning.

Poppy Education: Designing and Evaluating Educational Robotics Kits

Participants : Pierre-Yves Oudeyer, Didier Roy [correspondant] , Thibault Desprez.

The Poppy Education project aims to create, evaluate and disseminate all-inclusive pedagogical kits, open-source and low cost, for teaching computer science and robotics in secondary education and higher education, scientific literacy centers and Fablabs.

It is designed to help young people to take ownership with concepts and technologies of the digital world, and provide the tools they need to allow them to become actors of this world, with a considerable socio-economic potential. It is carried out in collaboration with teachers and several official french structures (French National Education, High schools, engineering schools, ...).

Poppy Education is based on the robotic platform poppy (open-source platform for the creation, use and sharing of interactive 3D printed robots), including:
Figure 31. Home page on http://poppy.local
IMG/homepage.png
Figure 32. The visual programming system Snap
IMG/snap.png
Figure 33. V-rep
IMG/vrep.png
Figure 34. 3D viewer
IMG/3d_viewer.png
Pedagogical experimentations : Design and experiment robots and the pedagogical activities in classroom.

The robots are designed with the final users in mind. The pedagogical tools of the project (robots and resources) are being created directly with the users and evaluated in real life by experiments. So teachers and researchers co-create activities, test them with students in class-room, share their experience and develop the platform as needed [126].

The activities were designed mainly with Snap! and Python. Most activities use Poppy Ergo Jr, but some use Poppy Torso (mostly in higher school due to its cost).

The pedagogical experiments in classroom carried out during the first year of the project notably allowed to create and experiment many robotic activities. These activities are designed as pedagogical resources introducing robotics. The main objective of the second year was to make all the activities and resources reusable (with description, documentation and illustration) easily and accessible while continuing the experiments and the diffusion of the robotic kits.

Figure 35. Experiment robots and pedagogical activities in classroom
IMG/robotics_in_classroom.jpg
Pedagogical documents and resources
Evaluation of the pedagogical kits

The impact of educational tools created in the lab and experimented in class had to be evaluated qualitatively and quantitatively. First, the usability, efficiency and user satisfaction must be evaluated. We must therefore assess, at first, if these tools offer good usability (i.e. effectiveness, efficiency, satisfaction). Then, in a second step, select items that can be influenced by the use of these tools. For example, students' representations of robotics, their motivation to perform this type of activity, or the evolution of their skills in these areas. In 2017 we conducted experiments to evaluate the usability of kits. We also collected data on students' perceptions of robotics.
Partnership on education projects

previous Previous | up Home | Next next