Vanda Luengo

Sorbonne University | UPMC · Laboratoire d'informatique de Paris 6 (LIP6)

Predictive student models are increasingly used in learning environments. However, due to the rising social impact of their usage, it is now all the more important for these models to be both sufficiently accurate and fair in their predictions. To evaluate algorithmic fairness, a new metric has been developed in education, namely the Model Absolute...

The eLearning specification xAPI, which employs a shared format for receiving and transmitting data, is used to collect data about the diverse range of experiences within online learning activities, thereby enabling the exchange of knowledge between multiple systems. This paper presents Logstore xAPI, a plugin that emits Moodle events as xAPI state...

Predictive student models are increasingly used in learning environments due to their ability to enhance educational outcomes and support stakeholders in making informed decisions. However, predictive models can be biased and produce unfair outcomes, leading to potential discrimination against some students and possible harmful long-term implicatio...

Predictive models used in intelligent learning environments can suffer from biased and unfair representation. However, existing fairness metrics that are meant to capture these issues are only based on the models' predictive performances. In this paper, we propose a novel fairness metric that measures to what extent the models behave unfairly. In a...

Predictive student models are increasingly used in learning environments due to their ability to enhance educational outcomes and support stakeholders in making informed decisions. However, predictive models can be biased and produce unfair outcomes, leading to potential discrimination against some students and possible harmful long-term implicatio...

Videos are a powerful media to learn activities through guided physical training such as surgery, especially when they are produced following human learning models and not as "how-to" videos. However, their success greatly depends on how they are integrated into the extensive curricula of domains where learning occurs through guided practice. In th...

In this work, we propose a learning analytics implementation based on a model-driven engineering approach. It aims at assessing the benefits that could arise from such an implementation, when pedagogical resources are produced via publishing chains, that already use the same approach to produce documents. Previously, we have discussed these potenti...

Robot-Assisted Laparoscopic Surgery (RALS) is now prevalent in operating rooms. This situation requires future surgeons to learn Classic Laparoscopic Surgery (CLS) and RALS simultaneously. Therefore, along with the investigation of the differences in performance between the two techniques, it is essential to study the impact of training in RALS on...

Parmi toutes les décisions que doit prendre un enseignant dans sa pratique professionnelle, nous appelons décisions didactiques celles qui visent à permettre aux élèves l’étude d’un savoir à enseigner. Quel modèle pour comprendre ces décisions ? Nous présentons un modèle articulant deux cadres théoriques, la théorie des situations didactiques (TSD)...

Résumé : Parmi toutes les décisions que doit prendre un enseignant dans sa pratique professionnelle, nous appelons décisions didactiques celles qui visent à permettre aux élèves l’étude d’un savoir à enseigner. Quel modèle pour comprendre ces décisions ? Nous présentons un modèle articulant deux cadres théoriques, la théorie des situations didactiq...

Procrastination is a widespread self-regulatory failure. It consists in voluntarily delaying work despite expecting to be worse-off the day after. Procrastination impacts students’ performance and well-being. Therefore it is argued that universities could and should play a more active role in helping freshmen improve their time management. We desig...

Les questions des élèves sont utiles pour leur apprentissage et pour l'adaptation pédagogique des enseignants. Nous étudions ici la nature des questions posées en ligne par les étudiants et comment le vote sur ces questions peut être lié à l’apprentissage. Nous avons donc développé un schéma de codage, puis conçu un annotateur automatique que nous...

In Multi-player learning games (MPLG), learners interact with each other through game activities. This paper aims to establish the basis of automatic detection of peer interactions that could emerge from MPLG scenarios. The information provided by this detection could help learning game designers to construct scenarios fostering the interactions th...

Going beyond mere forum posts categorization is key to understand why some students struggle and eventually fail in MOOCs. We propose here an extension of a coding scheme and present the design of the associated automatic annotation tools to tag students' questions in their forum posts. Working of four sessions of the same MOOC, we cluster students...

The analysis of students’ questions can be used to improve the learning experience for both students and teachers. We investigated questions (N = 6457) asked before the class by 1st year medicine/pharmacy students on an online platform, used by professors to prepare their on-site Q&A session. Our long-term objectives are to help professors in categ...

Multi-player Learning Games (MPLG) are immersive learning environments in which learners can actively participate. It is recognized in many learning contexts that the deployment of MPLG enables peer interaction, role play, learner empowerment through increased interactivity, personalized learning and experiential learning. A number of research have...

This paper describes the design and preliminary evaluations of AMBRE-KB. The goal of this authoring tool is to assist authors to elicit knowledge needed to design AMBRE ITSs without any programming. Such ITS enable learners to acquire a specific method in problem-solving. AMBRE-KB is based on meta-models of knowledge to be acquired. It supports the...

Automatic analysis of learners' questions can be used to improve their level and help teachers in addressing them. We investigated questions (N=6457) asked before the class by 1st year medicine/pharmacy students on an online platform, used by professors to prepare their on-site Q&A session. Our long-term objectives are to help professors in categor...

Analysis processes of learning traces, used to gain important pedagogical insights, are yet to be easily shared and reused. They face what is commonly called a reproducibility crisis. From our observations, we identify two important factors that may be the cause of this crisis: technical constraints due to runnable necessities, and context dependen...

Introduction: In 2006, the Grenoble-Alpes University Medical School decided to switch the learning paradigm of the first year to a blended learning model based on a flipped classroom with a continuous dual assessment system providing personal follow-up. We report a descriptive analysis of two pedagogical models. Methods: The innovative blended l...

Our objective is the design of a Virtual Learning Environment to train a person performing a work activity, to acquire non-technical skills during the experience of a critical situation. While the person’s performance level is due to carefully acquired technical skills, how it is maintained in front of criticality depends on non-technical skills, s...

Adaptation in learning environments can be performed according to various aspects, such as didactics, pedagogy or game mechanics. While most current approaches propose to adapt according to a single aspect, this paper proposes a Multi-Aspect Generic Adaptation Model (MAGAM). Based on the Q-matrix, this model aims at taking into account heterogeneou...

Multi-players learning games (MPLG) tend to foster learners’ engagement and immersion in learning games’ activities. They are an interesting way to organize learning situations in which learners interact with each other and solve challenges. In this context, teachers need to orchestrate MPLGs’ scenarios to arouse desired interactions such as cooper...

In most technical domains, non-technical skills have an influence on a worker’s performance. Studies have shown that these skills are most influential during critical situations, where usual technical procedures cannot be successfully applied. This article describes the challenges raised by the diagnosis of non-technical skills during critical situ...

Pour couvrir toutes les facettes des connaissances multimodales telles que les connaissances perceptivo-gestuelles, divers périphériques sont exploités. Les traces produites par ces derniers fournissent des informations pertinentes sur l’activité de l’apprenant. Cependant elles sont multi-sources et hétérogènes et, de ce fait, difficiles à traiter...

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 tutor...

Dans les EIAH, l'adaptation peut se faire suivant plusieurs aspects, notamment didactique, pédagogique, ludique, ou encore en fonction du contexte. Alors que les approches actuelles proposent d'adapter suivant un seul aspect, cet article propose le modèle d'adaptation générique M AGAM ayant la capacité à prendre en compte de multiples aspects dans...

Project MacCoy Critical aims to study and to improve training systems using simulation and virtual environments in medical education (obstetrics) and in driving education (novice drivers during the first months of autonomous driving). The paper describes and justifies the main concepts, the approach and the architecture elaborated from a multidisci...

In this paper we take a look at the difficulties raised by the teaching of the technical and non-technical skills mobilized during a critical situation, in the context of TEL within virtual environments. We present the advantages of using a combined enactive and situated learning approach to this problematic, and take an ill-defined perspective to...

This study aims at investigating which cues teachers detect and process from their students during instruction. This information capturing process depends on teachers’ sensitivity, or awareness, to students’ needs, which has been recognized as crucial for classroom management. We recorded the gaze behaviors of two pre-service teachers and two exper...

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...

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.

European universities are facing a massification of education, which leads to classes with the size of more than 1000 students in massive online courses (or in short “MOCs”, including the open version of MOOCs as a subcategory). This Grand Challenge Problem deals with the application of adaptive and adaptable educational technologies that exploit u...

Currently, many Learning Analytics (LA) initiatives are carried out throughout Europe. Typically, LA have been developed and are provided for one specific stakeholder group such as students or teachers of a university. In some cases the exploitation of technology usage data lacks the consideration of ethical issues, for instance if students are not...

This paper presents PeTra, a framework proposed forrepresenting and treating multi-source heterogeneous traces from intelligent learning environments. We tested the framework performance on traces from TELEOS, a simulation-based Intelligent Tutoring System (ITS) dedicated to percutaneous orthopedic surgery. This ITS captures learners’ interactions...

We present in this paper an algorithm for extracting perceptual-gestural rules from heterogeneous multisource traces. The challenge that we address is two-fold: 1) represent traces such that they render coherently all aspect of this multimodal knowledge; 2) ensure that key tutoring services can be produced on top of represented traces. In the spiri...

This paper presents PeTra, a framework proposed for representing and treating multi-source heterogeneous traces from simulated learning environments. We tested our proposition on traces from TELEOS, a simulation-based ITS dedicated to percutaneous orthopedic surgery. This ITS captures learners interactions from three different and independent sourc...

Cet article présente un framework de représentation et de traitement de traces multi-sources hétérogènes provenant d’EIAH dédiés aux domaines impliquant des connaissances perceptivo-gestuelles. La capture de traces perceptuelles et gestuelles dans un EIAH requiert l’utilisation coordonnée de plusieurs périphériques. La difficulté adressée est celle...

This paper presents DOP8: a Data Mining Iterative Cycle that improves the classical data life cycle. While the latter only combines the data production and data analysis phases, DOP8 also integrates the analysis operators life cycle. In this cycle, data life cycle and operators life cycle processing meet in the data analysis step. This paper also p...

Nous nous intéressons dans cet article à la problématique de l’acquisition des connaissances dans le cadre de la conception des EIAH. Dans le contexte du projet AMBRE, dont l’objectif est la conception d’EIAH destinés à apprendre des méthodes, nous souhaitons permettre à un utilisateur non informaticien d’expliciter les connaissances nécessaires à...

This paper presents our method based on similarity measure between contiguous pairs of sequences to yield automatic detection of significant behaviors from raw and continuous traces. The traces, produced by a simulation-based Intelligent Tutoring System dedicated to percutaneous orthopedic surgery, are related to perceptual-gestural behavior and il...

Le projet HUBBLE propose la création d'un observatoire pour la construction et le partage de processus d'analyse des traces e-learning massives. HUBBLE permettra aux différents acteurs (enseignants, apprenants, concepteurs, administrateurs ou politiques) d'analyser et d'expliquer les phénomènes d'enseignement et d'apprentissage avec des environneme...

Learners work increasingly with a large panel of learning environments that involve them in various activities thanks to a number of tools. These tools generate activity traces, which must then be taken into consideration and combined so as to establish the most accurate diagnosis about the learner's activity. This paper presents a diagnosis model,...

The purpose of the research presented in this paper is to design a computer-assisted human learning environment. The particular case under study is the intelligent tutoring system TELEOS (Technology Enhanced Learning Environment for Orthopaedic Surgery), which supports the learning of percutaneous orthopedic surgery, and specifically, vertebroplast...

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...

We describe a method to evaluate how student models affect ITS decision quality – their raison d’être. 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 sele...

Démonstration - Session : Traces et données d'observation

Session: Ingénierie pédagogique - http://www.irit.fr/EIAH2013/ - ISBN : 978-2-917490-22-8

Session: Traces et données d'observation - http://www.irit.fr/EIAH2013/ - ISBN : 978-2-917490-22-8

Session : Utilisation de techniques d'apprentissage automatique en EIAH - http://www.irit.fr/EIAH2013/index.php?page=programme

We have been working, during the last three years, in the context of our research team (multidisciplinary, with numerous and various TEL systems), on the design and implementation of an open platform to collect, save and share of experimental interaction data with TEL systems joined with the definition, save and share of analysis processes executed...

In the context of our research team (multidisciplinary with numerous and various TEL systems), we have been working during the last three years on the design and implementation of an open platform to collect, save and share experimental data drawn from the interaction with TEL systems, which could build, save and share analysis processes executed o...

In this paper we study one feedback process which is adapted to ill-defined domains. Indeed, this process use others aspects than expected solutions to propose a feedback. The feedback process is based in a set of didactical aspects. In particular, the feedback targets the control element of knowledge, i.e. the knowledge that allows to validate one...

Nominé pour Meilleur Papier - Session Scientifique 1: Diagnostic des connaissances & Assistance à la résolution de problèmes

Nowadays, Numeric Environments of Learning turn towards a consideration, in all its complexity, of the learner according to the education or the training dispensed. The problems of personalization, adaptation of the proposed activity to the learner have a repercussion on the diagnosis of knowledge of the learner. We are interested in this article i...

Eye tracking analysis allows the identification of the information taken into account by a user. Today, this approach is well known and proven. However, in domains such as simulation based learning environments, this analysis must take place during the activity, and with areas of interest that evolve opportunistically over time. Theses points are n...

Session EIAH - http://ic2012.crc.jussieu.fr/

Previous works have pointed out the crucial need for comparison between knowledge diagnostic tools in the field of Intelligent Tutoring Systems (ITS). In this paper, we present an approach to compare knowledge diagnostics. We illustrate our proposition by applying three criteria of comparison for various diagnostic tools in geometry.

Our aim is to develop a Fuzzy Logic based student model which removes the arbitrary specification of precise numbers and facilitates the modelling at a higher level of abstraction. Fuzzy Logic involves the use of natural language in the form of If-Then statements to demonstrate knowledge of domain experts and hence generates decisions and facilitat...

Section: Learner modeling

Volume: Interactions, Contextes et Traces - Ed. Hermès-Lavoisier - Direction: Jean Caussanel et Luigi Lancieri

L’objet de la recherche présentée dans cet article est la conception d’Environnement Informatique pour l’Apprentissage Humain. Le cas étudié est le Système Tutoriel Intelligent TELEOS (Technology Enhanced Learning Environment for Orthopaedic Surgery) supportant l’apprentissage de la chirurgie orthopédique percutanée, plus précisément la vertébropla...