Esteban Villalobos, a member of the TALENT team, defended his thesis entitled Developing a learning analytics framework to understand the temporal behavior of students in blended learning environments on 28 June 2024.

Congratulations to him!!!!!!!!

The jury was composed of:

• Hendrik Drachsler – DIPF, Deutsches Institut für Internationale Pädagogische Forschung
• Alejandra Martínez Monés – Universidad de Valladolid
• Sasha Poquet – Technical University of Munich
• Mohammed Saqr – University of Eastern Finland
• Mar Pérez-Sanagustín – IRIT, Université de Toulouse
• Julien Broisin – IRIT, Université de Toulouse

Abstract of the thesis:

In the evolving landscape of educational technology, Self-Regulated Learning (SRL) emerges as a pivotal factor for student success. This is increasingly prevalent in Blended Learning (BL) environments, where students are required to regulate their learning more effectively. Recognizing the critical role of SRL, this thesis addresses the gap in understanding SRL within BL settings by leveraging recent Learning Analytics (LA) methods with self-reported measures. Recent advancements in LA have introduced novel methods using Sequence Analysis (SA) for measuring SRL, offering more nuanced insights into student learning processes and strategies. The thesis addresses two primary objectives: (1) to develop an analytical framework to analyze SRL as it unfolds over time in BL settings, integrating both personal characteristics and trace data to examine the evolution of SRL strategies, and (2) leveraging this framework to understand how LA interventions affect the students’ behavior. To address the first objective, this thesis explores how students’ self-reported measures and prior achievements are related to students’ learning strategies detected using novel SA methods. Additionally, this thesis aims to answer the question of whether trace data can be considered a mediator between the students’ personal characteristics and their final course performance. To address the second objective, this thesis shows how SA methods can be used to understand the causal effect of an LA intervention in the temporal dynamics of students’ behavior. Through meticulous analysis, the research uncovers nuanced insights into how SRL manifests across various BL courses, the predictive value of students’ strategies on academic performance, and the transformative impact of LA interventions on learning behaviors. By synthesizing findings from multiple courses, this research contributes significantly to the educational technology field. The outcomes underscore the importance of a nuanced understanding of SRL in BL environments and demonstrate the benefits of leveraging LA and personal characteristics to understand students’ SRL.

The TALENT team was pleased to welcome Mohammed Saqr and Sasha Poquet who presented their work at IRIT on 28 June 2024.

1 – Learning analytics for social interactions in digital learning

Learning analytics, defined as the collection, analysis, and measurement of data collected in learning settings, have been a part of the scholarly discourse now for over a decade. Against this backdrop, learning analytics researchers aspire to demonstrate how analysis of learner traces can impact teaching and learning. Addressing such a call for impact today is more feasible in some areas of LA, such as predictive modelling, writing analytics, and analytics of self-regulation processes. However, some areas of LA have not advanced to offer the trusted insights. Among areas in need of refinement and rigor in learning analytics is the analysis of interpersonal activity in digital learning. Interpersonal activity among students when they learn, captured through social interactions, is known to contribute to the quality of learning and student experiences. The talk will offer two examples where analytics of learner granular behaviour can inform teaching practice on supporting interpersonal interactions in learning scenarios.

Presenter: Sasha POQUET

Oleksandra Poquet (Sasha Poquet) is a tenure-track professor in learning analytics at the School of Social Sciences and Technology the Technical Univerity of Munich. Prof. Dr Poquet leads a LEAPS research group that studies LEarning Analytics and Practices in Systems. Prof. Dr Poquet is a core member of the Munich Data Science Institute and a thematic lead on the use of process data to inform learning at the TUM’s EdTech Centre. She is also an external affiliate of the Centre for Change and Complexity in Learning, University of South Australia. From 2017-2021, she has served on the Executive Committee at the Society for Learning Analytics Research (SoLAR), as its Vice President in 2019-2021. Dr Poquet has been a convener of the series of workshops on networks in learning analytics and has edited a special issue on this topic for the Journal of Learning Analytics.

Website: https://www.edu.sot.tum.de/leaps/about/prof-dr-oleksandra-poquet/

2 – Precision Education: Mapping the person where the learning process takes place

The emphasis on the “self” or the “person” has been a central concept in several learning theories, methodologies, and approaches for decades and the literature is awash with notions of personalized, adaptive, and student-centered education. Nonetheless, research is commonly conducted using variable-centered methods where data is collected from a “group of others” to devise the average learner’s behavior. Yet, the average is barely representative of the breadth of human diversity. On the contrary, person-specific (or idiographic) methods aim to accurately and precisely model the individual person, create person-specific models, and devise unique parameters for each individual. Modeling the person —where the learning process takes place— paves the way for personalized, accurate, and precise education. The recent advancement in such methods, the expanding repertoire of tools and data collection methods could help answer the pressing question of what works for whom, and when? This presentation discusses the shortcomings of current methods, shows where and when they fall short, and introduces idiographic methods with recent literature.

Presenter: Mohammed SAQR

Mohammed Saqr is an Associate Professor of Computer Science at the School of Computing, University of Eastern Finland and leads UEF’s Learning Analytics Unit. Saqr has a PhD in Learning Analytics from Stockholm University, Sweden, followed by a postdoctoral position at Université Paris Cité, France. Later, he earned the title of Docent in Learning Analytics from the University of Oulu, Finland. His scholarly work is diverse and interdisciplinary and has received several recognitions (e.g., best papers at LAK, ICCE, SITE, TEEM). Mohammed also received the most competitive Swedish and Finnish funding and serves on the board of several academic journals. His current work is focused –among others– on advancing solutions for precision artificial intelligence.

Webiste: https://saqr.me/

Esteban Villalobos, mathematical engineer, M.Sc. in computer science, and Ph.D. candidate in the TALENT team, presented a talk for Inria Chile.

In this talk, “Developing a data analysis framework to understand the temporal behavior of students”, he introduces an analytical framework designed to understand the temporal behavior of students in digital environments beyond traditional classrooms. By integrating data analysis techniques based on artificial intelligence, the presentation explores the evolution of students’ learning strategies, offering a detailed understanding of their behavior and how it is impacted by specific interventions.

Franck Silvestre, a member of the TALENT team, defended his Habilitation à diriger des recherches (HDR) entitled Évaluation formative et génération de feedbacks soutenues par la technologie (Technology-supported formative assessment and feedback generation) on 5 April 2024.

The jury was composed of :

Rapporteurs

• Philippe Dessus, Professor, Grenoble Alpes University
• Sébastien George, Professor, Le Mans University
• Élise Lavoué, Professor, Université Jean-Moulin Lyon 3

Examiners

• Frédéric Amblard, Professor, Toulouse Capitole University
• Grégoire Borst, Professor, Université Paris Cité
• Julien Broisin, Senior Lecturer HDR, Toulouse 3 Paul Sabatier University

This week, the TALENT team had the pleasure of welcoming Elaine Teixeira and Rafael Ferreira Mello in Toulouse for the second LAFE (Learning Analytics solutions to support On time Feedback) meeting. Their visit was also an opportunity for them to present their work in a two-part seminar: “Unplugged Learning Analytics in Education to Promote Inclusion in Global South” (Rafael) and “Learning Analytics in Introductory Programming” (Elaine).

The LAFE project aims at supporting mobility between Brasil, France and Chile. During this meeting, we had the opportunity to discuss the different tools we are developing related to timely feedback and we organized the next steps. We are preparing the website and we will share it with you soon.

The article by Rialy Andriamiseza, Franck Silvestre, Jean-François Parmentier and Julien Broisin proposing a new model for orchestrating formative assessment sequences has just been published. Check it out!

Rialy Andriamiseza successfully defended his thesis “Learning Analytics-Based Formative Assessment Recommendations for Technology-Enhanced Learning Practices” on Friday 25 November 2022, before a jury composed of Sebastien George, Elise Lavoué, Vanda Luengo, Philippe Dessus, Franck Silvestre and Julien Broisin.

Congratulations to him!

Abstract: Formative assessment is a useful teaching method for improving learning and teaching. Providing teachers and learners with feedback designed to help them reach the learning objectives is at the core of every formative assessment processes. To conduct large scale formative assessment, technology-enhanced formative assessment systems emerged to support the usage of formative assessment processes. These systems generate data that can serve as a basis for improving these processes and services they provide. Consequently, we tackle the following research questions:Which useful information can be inferred from the analysis of data gathered from a tool implementing formative assessment processes used in authentic contexts? How can such information contribute to improve formative assessment processes orchestration? Based on literature and using a dataset gathered from the use of a formative assessment tool named Elaastic, we use learning analytics to provide evidence-based knowledge about formative assessment practices. This knowl- edge led us to design (i) recommendations for system designers of formative assessment tools (ii) recommendations for teachers orchestration of formative assessment sequences (iii) an orchestration model to assist teachers decision- making during the sequence.Afterwards, we put this orchestration model to the test by implement- ing it within Elaastic through explainable recommendations and collecting data of its usage. The analysis of these data provides evidences that show that (1) teachers do not follow the recommendations and (2) if teachers had followed them, there would be significantly improved benefits for learners. Future works discuss the way our orchestration model could be improved and expanded to other contexts.

Last 12th and 13th September 2022 TALENT had the honour to host the meeting of the European Project PROF-XXI. Visitors from Guatemala, Colombia, Spain and Portugal participated in the event.

Linked to this event, we organised an open session to discuss about Experiences and policies to promote hybrid education. We counted, in this case, with the participation of António Teixeira (Universidade Aberta de Portugal) as a keynote, participants of the project to present their experiences in Latin America and another round table with experts from France. Here you have name of the participants and their affiliations.  

The event was a success, with more than 40 people attending.

Participants Round table Experiences in Latin America:

• Mario Solarte, Asociado Universidad del Cauca, Colombia;  
• Carlos Delgado Kloos, Catedrático Universidad Carlos III de Madrid, España; 
• Miguel Morales, Director del Área de Educación Digital, Universidad Galileo, Guatemala; 
• Olga Lucía Saavedra Villega, Directora CEA USB;
• JORGE MALDONADO MAHAUAD, Director CEA Universidad de Cuenca.

Participants Round table Experiences in France:

• Claude Maranges, Directeur du Département Formation et Vie Etudiante, Université Fédérale Toulouse Midi Pyrénées (claude.maranges@univ-toulouse.fr);
• Alain Bérard, Directeur adjoint du C2IP – Centre d’Innovation et d’Ingénierie Pédagogiques de l’INSA Toulouse (alain.berard@insa-toulouse.fr);
• Patrice Terrier, Vice-président délégué au développement des usages du numérique et des systèmes d’information Université Tolouse II – Jean Jaurès (patrice.terrier@univ-tlse2.fr);
• Sylvain Crémoux, Chargé de mission Développement et évaluation des formations et des enseignements (sylvain.cremoux@cnrs.fr);
• Elodie Guillon, Cheffe de projet THE Campus – Hybridation des formations, Université de Toulouse.

You can have a look at the main results obtained from the project in the website of the project.

The entire TALENT team is proud to have organized the ECTEL 2022 conference! This international conference took place in Toulouse from September 12 to 16 in the premises of the ENSEEIHT school.

In parallel to the organization of the conference, Esteban Villalobos presented a paper for which he received the best paper award. Mar Pérez-Sanagustín also presented a paper, and Esther Félix a poster for her short paper.

The paper by Esteban Villalobos Supporting Self-regulated Learning in BL: Exploring learners’ tactics and strategies has won the best paper award at the 2022 ECTEL conference!

Last year (ECTEL 2021), it was Rialy Andriamiseza who won this award.