Search

Your search keyword '"Lallé, Sébastien"' showing total 40 results
Start Over Author "Lallé, Sébastien"

Refine your results

more »

more »

more »
40 results on '"Lallé, Sébastien"'

1. A Fair Post-Processing Method based on the MADD Metric for Predictive Student Models

Author

Verger, Mélina, Fan, Chunyang, Lallé, Sébastien, Bouchet, François, and Luengo, Vanda

Subjects
Computer Science - Computers and Society, Computer Science - Artificial Intelligence, Computer Science - Discrete Mathematics, Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

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 Density Distance (MADD). This metric enables us to measure how different a predictive model behaves regarding two groups of students, in order to quantify its algorithmic unfairness. In this paper, we thus develop a post-processing method based on this metric, that aims at improving the fairness while preserving the accuracy of relevant predictive models' results. We experiment with our approach on the task of predicting student success in an online course, using both simulated and real-world educational data, and obtain successful results. Our source code and data are in open access at https://github.com/melinaverger/MADD ., Comment: 1st International Tutorial and Workshop on Responsible Knowledge Discovery in Education (RKDE 2023) at ECML PKDD 2023, September 2023, Turino, Italy

Published
2024

2. Evaluating Algorithmic Bias in Models for Predicting Academic Performance of Filipino Students

Author

Švábenský, Valdemar, Verger, Mélina, Rodrigo, Maria Mercedes T., Monterozo, Clarence James G., Baker, Ryan S., Saavedra, Miguel Zenon Nicanor Lerias, Lallé, Sébastien, and Shimada, Atsushi

Subjects
Computer Science - Machine Learning, Computer Science - Computers and Society, K.3
Abstract

Algorithmic bias is a major issue in machine learning models in educational contexts. However, it has not yet been studied thoroughly in Asian learning contexts, and only limited work has considered algorithmic bias based on regional (sub-national) background. As a step towards addressing this gap, this paper examines the population of 5,986 students at a large university in the Philippines, investigating algorithmic bias based on students' regional background. The university used the Canvas learning management system (LMS) in its online courses across a broad range of domains. Over the period of three semesters, we collected 48.7 million log records of the students' activity in Canvas. We used these logs to train binary classification models that predict student grades from the LMS activity. The best-performing model reached AUC of 0.75 and weighted F1-score of 0.79. Subsequently, we examined the data for bias based on students' region. Evaluation using three metrics: AUC, weighted F1-score, and MADD showed consistent results across all demographic groups. Thus, no unfairness was observed against a particular student group in the grade predictions., Comment: Published in proceedings of the 17th Educational Data Mining Conference (EDM 2024)

Published
2024
Full Text
View/download PDF

3. Is Your Model 'MADD'? A Novel Metric to Evaluate Algorithmic Fairness for Predictive Student Models

Author

Verger, Mélina, Lallé, Sébastien, Bouchet, François, and Luengo, Vanda

Abstract

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 implications. This has prompted research on fairness metrics meant to capture and quantify such biases. Nonetheless, so far, existing fairness metrics used in education are predictive performance-oriented, focusing on assessing biased outcomes across groups of students, without considering the behaviors of the models nor the severity of the biases in the outcomes. Therefore, we propose a novel metric, the Model Absolute Density Distance (MADD), to analyze models' discriminatory behaviors independently from their predictive performance. We also provide a complementary visualization-based analysis to enable fine-grained human assessment of how the models discriminate between groups of students. We evaluate our approach on the common task of predicting student success in online courses, using several common predictive classification models on an open educational dataset. We also compare our metric to the only predictive performance-oriented fairness metric developed in education, ABROCA. Results on this dataset show that: (1) fair predictive performance does not guarantee fair models' behaviors and thus fair outcomes; (2) there is no direct relationship between data bias and predictive performance bias nor discriminatory behaviors bias; and (3) trained on the same data, models exhibit different discriminatory behaviors, according to different sensitive features too. We thus recommend using the MADD on models that show satisfying predictive performance, to gain a finer-grained understanding on how they behave and regarding who and to refine models selection and their usage. Altogether, this work contributes to advancing the research on fair student models in education. Source code and data are in open access at https://github.com/melinaverger/MADD. [For the complete proceedings, see ED630829.]

Published
2023

4. Fairness of MOOC Completion Predictions Across Demographics and Contextual Variables

Author

Lallé, Sébastien, Bouchet, François, Verger, Mélina, Luengo, Vanda, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Olney, Andrew M., editor, Chounta, Irene-Angelica, editor, Liu, Zitao, editor, Santos, Olga C., editor, and Bittencourt, Ig Ibert, editor

Published
2024
Full Text
View/download PDF

5. A Framework to Counteract Suboptimal User-Behaviors in Exploratory Learning Environments: an Application to MOOCs

Author

Lallé, Sébastien and Conati, Cristina

Subjects
Computer Science - Artificial Intelligence
Abstract

While there is evidence that user-adaptive support can greatly enhance the effectiveness of educational systems, designing such support for exploratory learning environments (e.g., simulations) is still challenging due to the open-ended nature of their interaction. In particular, there is little a priori knowledge of which student's behaviors can be detrimental to learning in such environments. To address this problem, we focus on a data-driven user-modeling framework that uses logged interaction data to learn which behavioral or activity patterns should trigger help during interaction with a specific learning environment. This framework has been successfully used to provide adaptive support in interactive learning simulations. Here we present a novel application of this framework we are working on, namely to Massive Open Online Courses (MOOCs), a form of exploratory environment that could greatly benefit from adaptive support due to the large diversity of their users, but typically lack of such adaptation. We describe an experiment aimed at investigating the value of our framework to identify student's behaviors that can justify adapting to, and report some preliminary results., Comment: The AAAI 2019 Workshop on Plan, Activity, and Intent Recognition

Published
2021

6. A Moodle Plugin for Rich xAPI Data Logging

Author

Rotelli, Daniela, Noël, Yves, Lallé, Sébastien, Luengo, Vanda, Pesce, David, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Viberg, Olga, editor, Jivet, Ioana, editor, Muñoz-Merino, Pedro J., editor, Perifanou, Maria, editor, and Papathoma, Tina, editor

Published
2023
Full Text
View/download PDF

7. How to Repeat Hints: Improving AI-Driven Help in Open-Ended Learning Environments

Author

Lallé, Sébastien, Yalçın, Özge Nilay, Conati, Cristina, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Wang, Ning, editor, Rebolledo-Mendez, Genaro, editor, Matsuda, Noboru, editor, Santos, Olga C., editor, and Dimitrova, Vania, editor

Published
2023
Full Text
View/download PDF

9. Gaze-Driven Adaptive Interventions for Magazine-Style Narrative Visualizations

Author

Lallé, Sébastien, Toker, Dereck, and Conati, Cristina

Subjects
Computer Science - Human-Computer Interaction, H.5.2
Abstract

In this paper we investigate the value of gaze-driven adaptive interventions to support processing of textual documents with embedded visualizations, i.e., Magazine Style Narrative Visualizations (MSNVs). These interventions are provided dynamically by highlighting relevant data points in the visualization when the user reads related sentences in the MNSV text, as detected by an eye-tracker. We conducted a user study during which participants read a set of MSNVs with our interventions, and compared their performance and experience with participants who received no interventions. Our work extends previous findings by showing that dynamic, gaze-driven interventions can be delivered based on reading behaviors in MSNVs, a widespread form of documents that have never been considered for gaze-driven adaptation so far. Next, we found that the interventions significantly improved the performance of users with low levels of visualization literacy, i.e., those users who need help the most due to their lower ability to process and understand data visualizations. However, high literacy users were not impacted by the interventions, providing initial evidence that gaze-driven interventions can be further improved by personalizing them to the levels of visualization literacy of their users., Comment: \c{opyright} 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promo-tional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Published
2019
Full Text
View/download PDF

10. On the Influence on Learning of Student Compliance with Prompts Fostering Self-Regulated Learning

Author

Lallé, Sébastien, Conati, Cristina, Azevedo, Roger, Mudrick, Nicholas, and Taub, Michelle

Abstract

In this paper, we investigate the relationship between students' learning gains and their compliance with prompts fostering self-regulated learning (SRL) during interaction with MetaTutor, a hypermedia-based intelligent tutoring systems (ITS). When possible, we evaluate compliance from student explicit answers on whether they want to follow the prompts, When such answers are not available, "we mine" several student behaviors related to prompt compliance. These behaviors are derived from students' eye-tracking and interaction data (e.g., time spent on a learning page, number of gaze fixations on that page). Our results reveal that compliance with some, but not all SRL prompts provided by MetaTutor do influence learning. These results contribute to gain a better understanding of how students benefit from SRL prompts, and provides insights on how to further improve their effectiveness. For instance, prompts that do improve learning when followed could be the focus of adaptation designed to foster compliance for those students who would disregard them otherwise. Conversely, prompts that do not improve learning when followed could be improved based on further investigations to understand the reason for their lack of effectiveness. [For the full proceedings, see ED596512.]

Published
2017

11. Predicting Co-occurring Emotions from Eye-Tracking and Interaction Data in MetaTutor

Author

Lallé, Sébastien, Murali, Rohit, Conati, Cristina, Azevedo, Roger, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Roll, Ido, editor, McNamara, Danielle, editor, Sosnovsky, Sergey, editor, Luckin, Rose, editor, and Dimitrova, Vania, editor

Published
2021
Full Text
View/download PDF

12. A Data-Driven Student Model to Provide Adaptive Support During Video Watching Across MOOCs

Author

Lallé, Sébastien, Conati, Cristina, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Bittencourt, Ig Ibert, editor, Cukurova, Mutlu, editor, Muldner, Kasia, editor, Luckin, Rose, editor, and Millán, Eva, editor

Published
2020
Full Text
View/download PDF

13. The Impact of Student Individual Differences and Visual Attention to Pedagogical Agents During Learning with MetaTutor

Author

Lallé, Sébastien, Taub, Michelle, Mudrick, Nicholas V., Conati, Cristina, Azevedo, Roger, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, André, Elisabeth, editor, Baker, Ryan, editor, Hu, Xiangen, editor, Rodrigo, Ma. Mercedes T., editor, and du Boulay, Benedict, editor

Published
2017
Full Text
View/download PDF

14. Impact of Individual Differences on Affective Reactions to Pedagogical Agents Scaffolding

Author

Lallé, Sébastien, Mudrick, Nicholas V., Taub, Michelle, Grafsgaard, Joseph F., Conati, Cristina, Azevedo, Roger, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Traum, David, editor, Swartout, William, editor, Khooshabeh, Peter, editor, Kopp, Stefan, editor, Scherer, Stefan, editor, and Leuski, Anton, editor

Published
2016
Full Text
View/download PDF

15. A Comprehensive Study on Evaluating and Mitigating Algorithmic Unfairness with the MADD Metric.

Author

Verger, Mélina, Bouchet, François, Chunyang Fan, Luengo, Vanda, and Lallé, Sébastien

Subjects
PYTHON programming language, EDUCATIONAL outcomes, EDUCATIONAL support, ONLINE education, DISTRIBUTION (Probability theory)
Abstract

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 certain individuals and harmful long-term implications. This has prompted research on fairness metrics meant to capture and quantify such biases. Nonetheless, current metrics primarily focus on predictive performance comparisons between groups, without considering the behavior of the models or the severity of the biases in the outcomes. To address this gap, we proposed a novel metric in a previous work (Verger et al., 2023) named Model Absolute Density Distance (MADD), measuring algorithmic unfairness as the difference of the probability distributions of the model's outcomes. In this paper, we extended our previous work with two major additions. Firstly, we provided theoretical and practical considerations on a hyperparameter of MADD, named bandwidth, useful for optimal measurement of fairness with this metric. Secondly, we demonstrated how MADD can be used not only to measure unfairness but also to mitigate it through postprocessing of the model's outcomes while preserving its accuracy. We experimented with our approach on the same task of predicting student success in online courses as our previous work, and obtained successful results. To facilitate replication and future usages of MADD in different contexts, we developed an open-source Python package called maddlib (https://pypi.org/project/maddlib/). Altogether, our work contributes to advancing the research on fair student models in education. [ABSTRACT FROM AUTHOR]

Published
2024

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

Author

Lallé, Sébastien, Mostow, Jack, Luengo, Vanda, Guin, Nathalie, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Lane, H. Chad, editor, Yacef, Kalina, editor, Mostow, Jack, editor, and Pavlik, Philip, editor

Published
2013
Full Text
View/download PDF

18. Assistance in Building Student Models Using Knowledge Representation and Machine Learning

Author

Lallé, Sébastien, Luengo, Vanda, Guin, Nathalie, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Lane, H. Chad, editor, Yacef, Kalina, editor, Mostow, Jack, editor, and Pavlik, Philip, editor

Published
2013
Full Text
View/download PDF

19. Fuzzy Logic Representation for Student Modelling : Case Study on Geometry

Author

Goel, Gagan, Lallé, Sébastien, Luengo, Vanda, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Cerri, Stefano A., editor, Clancey, William J., editor, Papadourakis, Giorgos, editor, and Panourgia, Kitty, editor

Published
2012
Full Text
View/download PDF

23. An Automatic Comparison between Knowledge Diagnostic Techniques

Author

Lallé, Sébastien, Luengo, Vanda, Guin, Nathalie, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Cerri, Stefano A., editor, Clancey, William J., editor, Papadourakis, Giorgos, editor, and Panourgia, Kitty, editor

Published
2012
Full Text
View/download PDF

35. Assistance to build and compare knowledge diagnostic techniques

Author

Lallé, Sébastien, Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Université de Grenoble, Vanda Luengo, and Nathalie Guin

Subjects
Diagnostic des connaissances, Apprentissage autoamtique, Knowledge diagnostic, Machine learning, EIAH, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], Authoring tool, Modèle d'apprenant, ITS, Benchmark, Student modelling, Outil auteur
Abstract

Comparing and building knowledge diagnostic is a challenge in the field of Technology Enhanced Learning (TEL) systems. Knowledge diagnostic aims to infer the knowledge mastered or not by a student in a given learning domain (like mathematics for high school) using student traces recorded by the TEL system. Knowledge diagnostics are widely used, but they strongly depend on the learning domain and are not well formalized. Thus, there exists no method or tool to build, compare and evaluate different diagnostics applied on a given learning domain. Similarly, using a diagnostic in two different domain usually imply to implementing almost both from scratch. Yet, comparing and reusing knowledge diagnostics can lead to reduce the engineering cost, to reinforce the evaluation and finally help knowledge diagnostic designers to choose a diagnostic. We propose a method, refine in a first platform, to assist knowledge diagnostic designers to build and compare knowledge diagnostics, using a new formalization of the diagnostic and student traces. To help building diagnostics, we used a semi-automatic machine learning algorithm, guided by an ontology of the traces and the knowledge designed by the designer. To help comparing diagnostics, we use a set of comparison criteria (either statistical or specific to the field of TEL systems) applied on the results of each diagnostic on a given set of traces. The main contribution is that our method is generic over diagnostics, meaning that very different diagnostics can be built and compared, unlike previous work on this topic. We evaluated our work though three experiments. The first one was about applying our method on three different domains and set of traces (namely geometry, reading and surgery) to build and compare five different knowledge diagnostics in cross validation. The second experiment was about designing and implementing a new comparison criteria specific to TEL systems: the impact of knowledge diagnostic on a pedagogical decision, the choice of a type of help to give to a student. The last experiment was about designing and adding in our platform a new diagnostic, in collaboration with an expert in didactic.; Cette thèse aborde la thématique de la comparaison et de la construction de diagnostics des connaissances dans les Environnements Informatiques pour l'Apprentissage Humain (EIAH). Ces diagnostics sont utilisés pour déterminer si les apprenants maîtrisent ou non les connaissances ou conceptions du domaine d'apprentissage (par exemple math au collège) à partir des traces collectées par l'EIAH. Bien que ces diagnostics soient récurrents dans les EIAH, ils sont fortement liés au domaine et ne sont que peu formalisés, si bien qu'il n'existe pas de méthode de comparaison pour les positionner entre eux et les valider. Pour la même raison, utiliser un diagnostic dans deux domaines différents implique souvent de le redévelopper en partie ou en totalité, sans réelle réutilisation. Pourtant, pouvoir comparer et réutiliser des diagnostics apporterait aux concepteurs d'EIAH plus de rigueur pour le choix, l'évaluation et le développement de ces diagnostics. Nous proposons une méthode d'assistance à la construction et à la comparaison de diagnostics des connaissances, réifiée dans une première plateforme, en se basant sur une formalisation du diagnostic des connaissances en EIAH que nous avons défini et sur l'utilisation de traces d'apprenant. L'assistance à la construction se fait via un algorithme d'apprentissage semi-automatique, guidé par le concepteur du diagnostic grâce à une ontologie décrivant les traces et les connaissances du domaine d'apprentissage. L'assistance à la comparaison se fait par application d'un ensemble de critères de comparaison (statistiques ou spécifiques aux EIAH) sur les résultats des différents diagnostics construits. La principale contribution au domaine est la généricité de notre méthode, applicable à un ensemble de diagnostics différents pour tout domaine d'apprentissage. Nous évaluons notre travail à travers trois expérimentations. La première porte sur l'application de la méthode à trois domaines différents (géométrie, lecture, chirurgie) en utilisant des jeux de traces en validation croisée pour construire et appliquer les critères de comparaison sur cinq diagnostics différents. La seconde expérimentation porte sur la spécification et l'implémentation d'un nouveau critère de comparaison spécifique aux EIAH : la comparaison des diagnostics en fonction de leur impact sur une prise de décision de l'EIAH, le choix d'un type d'aide à donner à l'apprenant. La troisième expérimentation traite de la spécification et de l'ajout d'un nouveau diagnostic dans notre plateforme, en collaborant avec une didacticienne.

Published
2013

36. Comparaison de l'impact de techniques de diagnostic des connaissances sur l'apprentissage d'une stratégie d'aide

Author

Lallé, Sébastien, Mostow, Jack, Luengo, Vanda, Guin, Nathalie, Supporting Interaction and Learning by Experience (SILEX), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Université Lumière - Lyon 2 (UL2), Laboratoire d'Informatique de Grenoble (LIG), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), The Robotics Institute, Carnegie Mellon University [Pittsburgh] (CMU), MeTAH, Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), Bourse de thèse et mobilité de S. Lallé: Région Rhône-Alpes (France) et Institute of Education Sciences (U.S): subvention R305A080628 accordée à l'université Carnegie Mellon, and Lefevre, Marie

Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.EIAH] Computer Science [cs]/Technology for Human Learning, [SHS.EDU]Humanities and Social Sciences/Education, [SHS.EDU] Humanities and Social Sciences/Education, prédiction, [INFO.EIAH]Computer Science [cs]/Technology for Human Learning, Technique de diagnostic, classification automatique, aide, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

Session : Utilisation de techniques d'apprentissage automatique en EIAH - http://www.irit.fr/EIAH2013/index.php?page=programme; National audience; Nous décrivons une méthode pour comparer des techniques de diagnostic des connaissances en fonction de leur impact sur les prises de décision de l'EIAH. À partir de traces d'apprenants, nous utilisons une méthode de classification automatique pour prédire le résultat (succès ou échec) d'une aide donnée par l'EIAH, en prenant en considération des informations sur l'apprenant, la tâche et l'état des connaissances de l'apprenant. Il en résulte une stratégie d'aide apprise automatiquement et permettant de sélectionner dans une situation donnée l'aide ayant la probabilité la plus élevée de succès. Le moyen usuel mais coûteux d'évaluer une telle stratégie d'aide est de l'implémenter et de la tester sur de nouveaux apprenants, ce qui nécessite du temps et des moyens. Nous utilisons plutôt des données déjà collectées, où les aides sont données aléatoirement aux apprenants, pour simuler l'impact d'une stratégie d'aide. Nous comparons ensuite différentes stratégies d'aide basées sur différentes techniques de diagnostic. Nous avons testé notre méthode en utilisant les données du Reading Tutor (projet LISTEN), destiné à l'apprentissage de la lecture. Nous rapportons la précision de la prédiction de quatre techniques de diagnostic en validation croisée, puis comparons l'impact des stratégies d'aide basées sur ces techniques. Notre méthode fournit une métrique pour comparer différentes techniques de diagnostic fondées sur leur utilité pour les prises de décision de l'EIAH.

Published
2013

37. Assistance à la conception de techniques de diagnostic des connaissances

Author

Lallé, Sébastien, Luengo, Vanda, Guin, Nathalie, Bouhineau, Denis, C. Choquet, P. Dessus, M. Lefevre, J. Broisin, O. Catteau, P. Vidal, Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), MeTAH, Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Supporting Interaction and Learning by Experience (SILEX), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Université Lumière - Lyon 2 (UL2), Région Rhônes-Alpes (bourse de thèse), C. Choquet, P. Dessus, M. Lefevre, J. Broisin, O. Catteau, P. Vidal, and Projets LISTEN et TELEOS

Subjects
outil auteur, diagnostic des connaissances, [INFO.EIAH] Computer Science [cs]/Technology for Human Learning, apprentissage automatique, [SHS.EDU]Humanities and Social Sciences/Education, [SHS.EDU] Humanities and Social Sciences/Education, [INFO.EIAH]Computer Science [cs]/Technology for Human Learning
Abstract

Session: Traces et données d'observation - http://www.irit.fr/EIAH2013/ - ISBN : 978-2-917490-22-8; National audience; Cet article propose une méthodologie d'assistance pour la conception de techniques de diagnostic des connaissances. La principale contribution est une méthodologie indépendante tant du domaine que du type de technique de diagnostic. Elle permet ainsi la conception de plusieurs techniques de diagnostic pour un domaine sans nécessiter la modélisation de chaque outil indépendamment. La méthode est semi-automatique : elle repose sur une ontologie des connaissances utilisée pour guider un algorithme d'apprentissage automatique. Une expérimentation évalue cette méthodologie sur deux domaines différents, la chirurgie orthopédique et la lecture de l'anglais. Les résultats montrent que les techniques de diagnostic conçues présentent une précision de la prédiction supérieure à la classe majoritaire, en validation croisée. Les tests statistiques RMSE et AIC permettent également de comparer les performances des techniques conçues.

Published
2013

38. Réutilisation et comparaison de techniques de diagnostic des connaissances en EIAH

Author

Lallé, Sébastien, Supporting Interaction and Learning by Experience (SILEX), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Université Lumière - Lyon 2 (UL2), and SI LIRIS, Équipe gestionnaire des publications

Subjects
[INFO]Computer Science [cs], [INFO] Computer Science [cs]
Abstract

National audience; Dans les EIAH, les techniques de diagnostic des connaissances sont nombreuses, mais peu formalisées. Par conséquent, il est difficile de les comparer entre elles, de les évaluer et finalement des les réutiliser. Nous présentons ici une première proposition visant à cerner les enjeux et les limites actuelles du sujet, et la démarche envisagée pour aboutir à une comparaison automatique d’outils de diagnostic.

Published
2011

Catalog

Books, media, physical & digital resources
See catalog results