pdessus's news - LSE Grenoble

Scenarios de conception d'un dispositif d'accompagnement

Wed, 07 Sep 2011 15:40:34 CEST

Villiot-Leclercq, E., Dessus, P., Mandin, S., Zampa, V. & Loiseau, M. (accepte). Une approche par scenarios pour la conception d'un dispositif d'accompagnement en ligne. Recherche et Formation.

Cet article s?adresse a un public de formateurs interesses par la mise en place d?un dispositif d?accompagnement humain en ligne et partiellement automatise dans le cadre d?une formation a distance. Son propos est de presenter une methode de design pedagogique basee sur les scenarios, et d?en illustrer l?expression dans le cadre de la conception d?une situation d?assistance a la tache de comprehension de syntheses de textes. Cette situation a ete implantee dans une application en ligne afin de pouvoir etre mise en ?uvre en situation de formation universitaire.

Loops, gaps and contradiction: three core PLE objects

Sun, 29 May 2011 09:12:00 CEST

Dessus, P. (2011, 1st July). Loops, gaps and contradiction: Three core PLE functions that foster learning [Invited talk]. Milton Keynes: Knowledge Media Institute of the Open University (UK). [Site]

This talk is about some core objects encountered in PLEs that can cause or even foster learning. Literature on PLEs often reports the features every PLE share. The following are worth mentioning among the most frequently reported: personalisation and malleability of the learning environment, suitability for both formal and informal learning, focus on learner. Literature sometimes also reports the dimensions upon which any PLE can be analysed (Palmer et al., 2009; van Harmelen, 2006) or which processes are fostered in learning (Henri, Charlier & Limpens, 2008). Since reporting these features is sound from a technical viewpoint (though problematic for some researchers, see Fiedler & Valjataga, 2010), they seldom are psychologically grounded and the question of how they can help or even trigger learning can be posed.

My talk will address this question: to which extent a PLE can mimic some core activities involved in teaching, and through which functions or objects? In so doing, my view is not purely technical or functional but psychological. Every teacher knows that learning is more efficient when: the context is properly managed so that the content is explicitly or more implicitly showed, teacher and learners are both involved in an evaluative loop of the other's intentions, and careful guidance is given as well (Csibra, 2007; Dessus, Mandin & Zampa, 2008). I will argue in this talk that PLEs sharing such features can foster learning. In a nutshell, a PLE that fosters learning enable learners to be engaged,
1/ in several activity loops whose main goal is exhibiting some material for learning purposes,
2/ in so doing, explicitly or more implicitly, they can realize the gap between their actual state (epistemic or social) and their expected state (e.g., what what remains to be learned, with whom to interact);
3/ in parallel, they must have the opportunity to contradict (or at least negotiate) the feedback if it appears to be non optimal.

I will argue in the talk that is the very specific combination and learners' involvement or awareness of these three objects that fosters learning. I will first present in more depth the three objects, then I will illustrate these notions in giving some descriptions of the systems I co-designed and co-implemented in my lab (Apex 1.0, Apex 2.0, Resum? Web and Pensum), and will end the talk in giving some design principles for new PLEs to emerge from this view (Dessus, 2009). Beyond the explosion of the PLE features, due to ever-growing research progresses lies the problem of their complexity and possible non-use (Norman, 2011). Grounding the design and development of PLEs with psychology-oriented principles may prevent this problem.

Deliverable 7.4

Sun, 17 Apr 2011 11:43:50 CEST

This deliverable describes the objectives, approach, planning and results of the third pilot round, in which both individual and threaded services underwent validation. The two goals of this round were to provide input to the LTfLL exploitation plan and roadmap (deliverable 2.5). 531 participants (316 learners) took part in the pilots, which used LTfLL services based on five different languages. The average timespan of the pilots was three weeks and involved learners, tutors, teaching managers, the LTfLL team and Technology Enhanced Learning experts. The validation approach was based on Prototypical Validation Topics derived from the Round 2 validation topics, which refocused the validation topics on exploitation and allowed conclusions to be drawn across all services. Results demonstrated the areas of strength and weakness of each service, informing the selling points and barriers to adoption within the exploitation strategy, as well as suggesting possible further contexts of use. All services were noted to have high relevance in addressing burning issues for organizations, but further improvements to accuracy from a user viewpoint are required. Results on future enhancements to improve likelihood of adoption contribute to the roadmap. Results also provide an indication of each service's current readiness for adoption and provided insights into transferability issues. The overall conclusion is that some LTfLL services are more ready than others for adoption now, with some being currently more suited to sustainability in research settings.

Deliverable 2.5 (LTfLL)

Sun, 17 Apr 2011 11:43:09 CEST

This deliverable reports on a vision of the future for the LTLL tools and language technology for e-learning generally. The LTfLL tools and infrastructure are presented in terms of three layers (subsections), which are ultimately based on the final validation results. Layer one describes achievements and their importance. Layer two describes requiremets for adoption and sustain ability. And layer three describes logical extensions which could be made for any future versions of the tools. The report ends with a discussion of the future of language technology-based e-learning tools, with the guiding theme being personalisable tools for social learning.

Pensum, un systeme d'aide a la comprehension de cours (null)

Sun, 17 Apr 2011 11:41:58 CEST

Loiseau, M., Dupre, D. Dessus, P. (2011). Pensum, un systeme d'aide a la comprehension de cours a distance [Prix de la meilleure communication interdisciplinaire]. In M. Betrancourt, C. Depover, V. Luengo, B. De Lievre G. Temperman (Eds.), Conference EIAH 2011 (pp. 287?299). Mons : Presses de l'universite de Mons. [a href=http://w3a.umons.ac.be/~eiah2011/Site/a]brbrCet article a pour but de presenter Pensum, un systeme permettant a des etudiants a distance de produire des syntheses de cours dans le but de les comprendre, et d?en avoir des retours automatiques fondes sur une analyse semantique. Nous decrivons une premiere utilisation de ce logiciel, aupres de 17 etudiants de 2e annee de Master en sciences de l?education, ayant soit le role d?apprenant soit le role de tuteur, et analysons trois types de donnees : traces, bugs et questionnaire d?opinion. Les resultats montrent que les participants parviennent rapidement a utiliser les principales fonctionnalites de Pensum et que, s?il reste encore a le tester en situation reelle, son utilisabilite permet d?en faire un outil pouvant promouvoir l?apprentissage autoregule de cours a distance.

Pensum : un outil intelligent pour assister la compr(null)

Sun, 17 Apr 2011 11:40:57 CEST

Expose aux Rencontres d'Autrans 2011. Autrans, 13 janvier.

Automated free-text assessment: Some lessons learned

Sun, 17 Apr 2011 11:40:27 CEST

To Appear in IJCEELLbrbrMost of e-learning systems engage successively students in reading, writing and assessment activities. In the third phase, the teacher gives feedback on student?s comprehension, which is often processed a long time after the others, letting the students alone with their difficulties. Thus, there is room to devise automated assessment systems on course comprehension, based on NLP techniques like Latent Semantic Analysis (LSA). The aim of this paper is to present some systems devised to complete this aim, which implement LSA to model learners? comprehension and/or to compare reading material (e.g., course text) with learners? summaries about it, select reading materials and predict student processes from their summaries.

Validating a Computer-based Tutor

Sun, 28 Nov 2010 16:11:33 CET

Zampa, V. Dessus, P. (Accepted). Validating a computer-based tutor that promotes Self-Regulated Writing-to-Learn. In Y. Psaromiligkos, T. Spyridakos S. Retalis (Eds.), Evaluation in e-learning. New York: Nova Publishers.brbrWe introduce in this chapter Apex 2.1 (i.e., Assistant for Preparing EXams), a prototype system that provides automated feedback to e-learning students on the summaries they wrote about the courses they attended. First we present some theoretical underpinnings on how the system has been designed then we detail Apex 2.1 architecture. Eventually, the first results of a validation study involving three groups of stakeholders (students, teacher, administrator) are presented. The utility, acceptability and usability of the system are examined.

Conception de dispositifs hybrides

Sun, 21 Nov 2010 17:16:09 CET

Villiot-Leclercq, E., Charroud, C. Dessus, P. (2010). Conception de dispositifs hybrides : un exemple pour la formation C2i2e a l'IUFM de Grenoble. iSeacute;minaire du Pocirc;le Sud-Est des IUFM/i. Aix-en-Provence, IUFM Aix-Marseille, 18 novembre.

D5.3 Support and feedback services -

Wed, 13 Oct 2010 08:33:41 CEST

This report presents Version 1.5 of the Learning support and feedback services (delivering recommendations based on interaction analysis and on students? textual production) that can be integrated within an e-learning environment.brbrDescription: Trausan-Matu, S., Dessus, P., Rebedea, T., Loiseau, M., Dascalu, M., Mihaila, D., Braidman, I., Armitt, G., Smithies, A., Regan, M., Lemaire, B., Stahl, J., Villiot-Leclercq, E., Zampa, V., Chiru, C., Pasov, I., Dulceanu, A. (2010). D5.3 Support and feedback services version 2. LTfLL-project.

Implementing Bakhtin(null)

Wed, 21 Jul 2010 11:20:58 CEST

Dessus, P. Trausan-Matu, S. (2010). Implementing Bakhtin?s dialogism theory with NLP techniques in distance learning environments. In S. Trausan-Matu, P. Dessus, W. Greller, F. Wild C. Mauerhofer (Eds.),i Second Workshop on Natural Language Processing in Support of Learning: Metrics, Feedback and Connectivity (NLPsL 2010)./i. Bucharest (Romania).brbrThe purpose of this paper is to present and discuss a Natural Language Processing-based operationalization of Bakhtin?s dialogism ideas, and to insert it in the context of distance learning. Three core concepts from Bakhin are introduced and their application in the domain of distance learning discussed. Then, two computer-based systems based on these ideas, PolyCAFe and Pensum are presented.

Ecrire des resumes pour apprendre des cours

Mon, 12 Jul 2010 08:43:08 CEST

Cet article presente Apex 2.1 (pour Aide a la Preparation des EXamens). Il s'agit d'un systeme prototype donnant des retours automatiques a des etudiants realisant des resumes de cours, dans un contexte d'enseignement a distance. Nous presentons quelques donnees theoriques, puis l'architecture d?Apex 2.1, pour enfin decrire une etude le validant aupres de trois groupes d'utilisateurs potentiels (etudiants, enseignant ou administrateur), du point de vue de l'utilite, acceptabilite et utilisabilite de ce systeme.

Deliverable 7.3 (LTfLL)

Thu, 08 Jul 2010 18:16:11 CEST

This deliverable describes the objectives, approach, planning and results of the second pilot round, and updates the validation design for round 3. The objectives of the second pilot round were directed towards enhancing the quality of the software services in the next round and beginning to measure the success of the individual services. Validation activities took place at eight pilot sites with stakeholders (learners, tutors, teaching managers), preceded by technical verification. A small-scale study on transferability of the software took place within the LTfLL team. Results demonstrated that the LTfLL software provides effective solutions to pedagogic problems of feedback and knowledge acquisition, subject to enhancements identified during validation. There is strong evidence for integrating the feedback services with a knowledge acquisition service. Software elements for replacement or further development were identified. The transferability study showed that language technologies appear to be most appropriate for problem-based and self-regulated learning. A number of barriers to adoption were identified. In conclusion, the pilots have met their objectives for the second pilot round. The goals of the final pilot round are to support exploitation of the services through providing evidence of the utility of the services and factors affecting their adoption, and to inform the end of project road map, through extended full pilots and validation associated with dissemination activities.

Evaluarea si sumarizarea automata a conversatiilor chat

Thu, 08 Jul 2010 18:14:35 CEST

b 7-a Conferinta Nationala de Interactiune Om-Calculator (RoCHI 2010)./bbrOdata cu evolutia continua a mediilor colaborative, nevoia unei analize automate in vederea evaluarii participantilor la discutii de tip Instant Messenger (chat) a devenit din ce in ce mai acuta. De asemenea, o facilitate necesara a unui sistem de notare si evaluare a replicilor si, implicit, a participantilor este sumarizarea. In vederea atingerii acestor obiective, pe de o parte, o serie de factori bazati pe procesarea limbajului natural (inclusiv analiza semantica prin intermediul Latent Semantic Analysis - LSA) si data-mining au fost luati in considerare. Pe de alta parte, in scopul unei evaluari minutioase si multi-perspectiva a participantilor, au fost calculate masuri derivate din metodele lui Page de notare a eseurilor, lizibilitate si analiza retelei sociale. In vederea evaluarii performantelor sistemului un standard de aur a fost utilizat pentru determinarea corectitudinii rezultatelor obtinute.

NLP in support of Learning 2010 [Workshop]

Fri, 04 Jun 2010 11:14:56 CEST

The purpose of this workshop is to focus on using language technologies in support of learning and teaching - by trying to identify what questions and problems are solved, but also to raise and discuss how well the metrics and algorithms developed assist in the provision of support and the construction of feedback for learning. What are the most efficient ways? To what extent do they match distances inferred by a teacher's assessments? The workshop addresses the problem of how support can be provided and feedback be generated in order to help students learn and teachers to assess their progress.brbrSeveral Natural Language Processing techniques like Latent Semantic Analysis (LSA) or the use of semantic and pragmatic analysis of conversations have been successfully deployed in various educational applications to enrich learning and teaching with information technology. However, few research approaches considered also in detail the problem of providing feedback.

Chercheurs 2.0 : Nouvelles (?) habitudes de travail

Sun, 04 Apr 2010 13:48:00 CEST

In P. Dessus L. Perrillat (orgs), Demi-journee d'etude chercheurs 2.0.brbrLa generalisation des outils informatiques et plus recemment l'arrivee des outils Web 2.0 a-t-elle fondamentalement change les habitudes de travail des chercheurs ? Notre propos est de repondre a cette question, en faisant le point sur les principaux changements, mais aussi les invariants dans les habitudes. Nous evoquerons ensuite les opportunites mais aussi les problemes poses par ces outils, pour conclure sur ce que pourrait etre l'activite du chercheur dans un proche avenir, avec les outils actuellement en cours de developpement.

Les TUIC ont-elles un effet sur l'apprentissage?

Mon, 29 Mar 2010 18:31:00 CEST

Les TICE (Technologies de l'information et de la communication appliquees a l'education) sont maintenant bien presentes dans la plupart des ecoles francaises. On s'accorde a leur trouver un interet pour acceder a l'information, mais aussi pour developper des competences qui seront utiles dans la vie professionnelle future des eleves. Pour autant, utiliser les TUIC amene-t-il necessairement un effet reel sur l'apprentissage des eleves ? A quel age peut-on commencer a les utiliser ? Cette utilisation n'est-elle pas sans inconvenients ? Ces differentes questions seront illustrees de quelques etudes faisant intervenir les TUIC dans un environnement scolaire, avec une centration sur l'enseignement en ecole maternelle et elementaire.

Assessing Writing Collaboration in Learning

Mon, 29 Mar 2010 18:29:14 CEST

We describe the main tasks students usually complete when working in an e-learning platform, across five mean features that have to be taken into account in research efforts (writing-based activities, individual/collective level, knowledge/ pedagogy orientation, feedback, multiple stakeholders account). Ways to analyse and assist these tasks by (semi)-automatic assessments using NLP techniques is eventually discussed.

Un EIAH d'aide a la redaction de syntheses

Mon, 22 Mar 2010 08:43:02 CET

Helping students understand courses through written syntheses

Sun, 28 Feb 2010 09:30:11 CET

In a life-long learning context, learners have to perform a lot of writing-based activities like document analysis that are seldom assessed by teachers or tutors because this assessment is time-consuming. Current computer-based methods that (semi)-automatically assess free texts have two main drawbacks. They are seldom integrated in a rational and comprehensive workflow. They also seldom rely on effective learning activities (e.g., synthesis writing). The goal of the article is to propose a service, Pensum, integrated in a PLE that helps students to understand a course content through writing a synthesis. Based on both natural language processing techniques, iPensum/i proposes just-in-time and reflexive feedback on a writing task like document synthesis.

Utterances assessment and summarization in chat conversations

Sun, 10 Jan 2010 10:11:29 CET

LTfLL - D 5.2 - Learning Support and Feedback

Sat, 19 Dec 2009 16:21:13 CET

This report presents Version 1 of the support and feedback services (delivering recommendations based on interaction analysis and on students? textual production) that can be integrated within an e-learning environment. Further steps toward the implementation of Version 2 of these services and their future integration with all the LTfLL services are also suggested.

LTfLL Consortium's Approach to Integration

Sun, 13 Dec 2009 11:23:45 CET

This report describes the LTfLL approach to integrate the support and advice services developed in the project. The approach comprises theoretical, methodological, technological, and dissemination and validation perspectives. The theoretical layer, based on a common theoretical framework, elaborates on how the services can support learners in both collaborative and individual knowledge building processes. The methodological layer argues the services can be combined in different ways to support learners and tutors in different educational settings, but that stakeholders? needs should be taken into account. The layer exemplifies this presenting an integrated scenario that illustrates how the LTfLL services can support learners in an institutional context. Afterwards, the technical layer describes how the LTfLL services could be integrated into an existing community-based learning management system to provide learners with a personal learning environment. The validation and dissemination layer discusses the additional strategies needed for the integrated approach. Finally, the report presents conclusions and outlines future work.

LTfLL - D 7.2 - Validation Design

Sun, 13 Dec 2009 11:23:31 CET

This deliverable describes the objectives, approach, planning and results of the first pilot round, and updates the validation design for round 2. The objectives of the first pilot round were directed towards enhancing the quality of the scenarios and services in the next round, through validation activities with stakeholders and technical verification. Results demonstrated that showcase scenarios described realistic solutions to real stakeholder problems, subject to enhancements identified during validation. Software elements for replacement or further development were identified. In conclusion, the pilots indicate that the utility of advanced learning technologies can be generalized across different stakeholder groups and pedagogic problems, in the areas of positioning, feedback and knowledge sharing. In the second round, the validation objectives are extended to provide an early evaluation of the project using primarily quantitative methods, while continuing formative stakeholder evaluation and requirements gathering activities.