2025

• Preprint IntEnsES: INTeractions Enseignant-Étudiants dans le Supérieur
  L. Lardy and P. Dessus
  May 2025
   PDF HAL[BibTeX][Abstract]

  @unpublished{lardy:hal-05065437,
    title = {{IntEnsES: INTeractions Enseignant-{\'E}tudiants dans le Sup{\'e}rieur}},
    author = {Lardy, Laurent and Dessus, Philippe},
    hal_version = {v1},
    hal_id = {hal-05065437},
    pdf = {https://hal.science/hal-05065437v1/file/Intenses-v-4-0-8.pdf},
    keywords = {Syst{\`e}me d'observation ; Interactions enseignant-{\'e}tudiants ; Enseignement sup{\'e}rieur},
    month = {May},
    year = {2025},
    note = {working paper or preprint},
    url = {https://hal.science/hal-05065437},
    abstract = {Ce document présente un système d'observation de la qualité des interactions enseignant-étudiants dans l'enseignement supérieur. Dans un premier temps, nous présenterons l’engagement et l’autorégulation de l’apprentissage. Ensuite, nous montrerons comment la théorie de l’autodétermination (TAD) fournit un cadre pertinent pour évaluer les interactions enseignant-étudiants qui nourrissent ces deux facteurs explicatifs de la réussite académique et de la qualité de l’apprentissage. Enfin nous proposerons un outil de cotation des interactions enseignants-étudiants qui permette de les évaluer en référence au cadre que nous proposons. Il est à noter que cet outil n’évalue pas la qualité du contenu disciplinaire proposé. Dans l’enseignement supérieur, cette évaluation nécessiterait des connaissances pointues dans le domaine observé ce qui réserverait l’usage du système d’observation à des spécialistes de la discipline et limiterait grandement son applicabilité.},
  }

  Ce document présente un système d'observation de la qualité des interactions enseignant-étudiants dans l'enseignement supérieur. Dans un premier temps, nous présenterons l’engagement et l’autorégulation de l’apprentissage. Ensuite, nous montrerons comment la théorie de l’autodétermination (TAD) fournit un cadre pertinent pour évaluer les interactions enseignant-étudiants qui nourrissent ces deux facteurs explicatifs de la réussite académique et de la qualité de l’apprentissage. Enfin nous proposerons un outil de cotation des interactions enseignants-étudiants qui permette de les évaluer en référence au cadre que nous proposons. Il est à noter que cet outil n’évalue pas la qualité du contenu disciplinaire proposé. Dans l’enseignement supérieur, cette évaluation nécessiterait des connaissances pointues dans le domaine observé ce qui réserverait l’usage du système d’observation à des spécialistes de la discipline et limiterait grandement son applicabilité.

• Report Acceptance Assessment of CACs in Educational Context
  P. Dessus, S. Cojean, C. Michel, C. Hanner, R. Laurent, L. Gimeno and Q. Le Bideau
  May 2025
   HAL[BibTeX][Abstract]

  @techreport{dessus:hal-05065379,
    title = {{Acceptance Assessment of CACs in Educational Context}},
    author = {Dessus, Philippe and Cojean, Salom{\'e} and Michel, Christine and Hanner, Carole and Laurent, Romain and Gimeno, Line and Le Bideau, Quentin},
    hal_version = {v1},
    hal_id = {hal-05065379},
    keywords = {Context-aware classroom ; Acceptance assessment},
    month = {May},
    year = {2025},
    institution = {{Univ. Grenoble Alpes (France)}},
    number = {Deliverable A.2},
    url = {https://hal.science/hal-05065379},
    abstract = {This report examines the opinions of the various stakeholders likely involved in a Context- Aware Classroom (CAC) regarding its acceptance and acceptability in an academic environment. This opinion is important because, if unfavorable, it will hinder its use. After reviewing the main models of technology acceptance and acceptability, we focus on CACs to examine a few studies, still rare, that focus on these parameters. We then detail 5 empirical studies on the acceptance of new educational technologies. Study 1 and 2 are about the acceptability of AI-based educational systems and generative AI systems, respectively. The other three studies are mostly devoted to CACs. Study 3 questions the values attached to the future use (acceptability) of CACs. Study 4 is about their acceptance, since participants actually had classes in CACs. Eventually, Study 5 explores the design and prototyping of CACs and learning analytics-based systems to monitor students’ engagement, implementing a UX design method: personas.},
  }

  This report examines the opinions of the various stakeholders likely involved in a Context- Aware Classroom (CAC) regarding its acceptance and acceptability in an academic environment. This opinion is important because, if unfavorable, it will hinder its use. After reviewing the main models of technology acceptance and acceptability, we focus on CACs to examine a few studies, still rare, that focus on these parameters. We then detail 5 empirical studies on the acceptance of new educational technologies. Study 1 and 2 are about the acceptability of AI-based educational systems and generative AI systems, respectively. The other three studies are mostly devoted to CACs. Study 3 questions the values attached to the future use (acceptability) of CACs. Study 4 is about their acceptance, since participants actually had classes in CACs. Eventually, Study 5 explores the design and prototyping of CACs and learning analytics-based systems to monitor students’ engagement, implementing a UX design method: personas.

2024

• Report Context-Aware Classrooms: legal and ethical issues (Deliverable DA.1)
  P. Dessus, T. Petelin, R. Laurent, H. El Kechai and S. Cojean
  September 2024
   HAL[BibTeX][Abstract]

  @techreport{dessus:hal-04753885,
    title = {{Context-Aware Classrooms: legal and ethical issues (Deliverable DA.1)}},
    author = {Dessus, Philippe and Petelin, Tanja and Laurent, Romain and El Kechai, Hassina and Cojean, Salom{\'e}},
    hal_version = {v1},
    hal_id = {hal-04753885},
    keywords = {Context-Aware Classrooms ; Ethics ; Legal aspects ; Value-sensitive design},
    month = {September},
    year = {2024},
    institution = {{Univ. Grenoble Alpes}},
    url = {https://hal.science/hal-04753885},
    abstract = {This report presents the legal and ethical grounds of the TALISMAN project, aimed at capturing and analyzing pedagogical events within Context-Aware Classrooms, or CACs), analyzed globally, without individual account. The legal aspects are mainly discussed in line with the EU General Data Protection Regulation and the ethical aspects are subject to an analysis using the Value Sensitive Design framework. Then a two-fold questionnaire aiming at identifying CACs users, either directly or indirectly affected by them and at eliciting their values, is presented.},
  }

  This report presents the legal and ethical grounds of the TALISMAN project, aimed at capturing and analyzing pedagogical events within Context-Aware Classrooms, or CACs), analyzed globally, without individual account. The legal aspects are mainly discussed in line with the EU General Data Protection Regulation and the ethical aspects are subject to an analysis using the Value Sensitive Design framework. Then a two-fold questionnaire aiming at identifying CACs users, either directly or indirectly affected by them and at eliciting their values, is presented.

• Proceedings Exploring VQ-VAE with Prosody Parameters for Speaker Anonymization
  S. Leang, A. Augusma, E. Castelli, F. Letué, S. Sam and D. Vaufreydaz
  Voice Privacy Challenge 2024 at INTERSPEECH 2024, Kos Island, Greece, September 2024
   PDF HAL[BibTeX][Abstract]

  @inproceedings{leang:hal-04706860,
    title = {{Exploring VQ-VAE with Prosody Parameters for Speaker Anonymization}},
    author = {Leang, Sotheara and Augusma, Anderson and Castelli, Eric and Letu{\'e}, Fr{\'e}d{\'e}rique and Sam, Sethserey and Vaufreydaz, Dominique},
    booktitle = {{Voice Privacy Challenge 2024 at INTERSPEECH 2024}},
    hal_version = {v1},
    hal_id = {hal-04706860},
    pdf = {https://inria.hal.science/hal-04706860v1/file/VQVAEForSpeakerAnonymization.pdf},
    keywords = {speech anonymization ; speech synthesis ; vectorquantized variation auto-encoder ; emotional state},
    month = {September},
    year = {2024},
    address = {Kos Island, Greece},
    url = {https://inria.hal.science/hal-04706860},
    abstract = {Human speech conveys prosody, linguistic content, and speaker identity. This article investigates a novel speaker anonymization approach using an end-to-end network based on a Vector-Quantized Variational Auto-Encoder (VQ-VAE) to deal with these speech components. This approach is designed to disentangle these components to specifically target and modify the speaker identity while preserving the linguistic and emotionalcontent. To do so, three separate branches compute embeddings for content, prosody, and speaker identity respectively. During synthesis, taking these embeddings, the decoder of the proposed architecture is conditioned on both speaker and prosody information, allowing for capturing more nuanced emotional states and precise adjustments to speaker identification. Findings indicate that this method outperforms most baseline techniques in preserving emotional information. However, it exhibits more limited performance on other voice privacy tasks, emphasizing the need for further improvements.},
  }

  Human speech conveys prosody, linguistic content, and speaker identity. This article investigates a novel speaker anonymization approach using an end-to-end network based on a Vector-Quantized Variational Auto-Encoder (VQ-VAE) to deal with these speech components. This approach is designed to disentangle these components to specifically target and modify the speaker identity while preserving the linguistic and emotionalcontent. To do so, three separate branches compute embeddings for content, prosody, and speaker identity respectively. During synthesis, taking these embeddings, the decoder of the proposed architecture is conditioned on both speaker and prosody information, allowing for capturing more nuanced emotional states and precise adjustments to speaker identification. Findings indicate that this method outperforms most baseline techniques in preserving emotional information. However, it exhibits more limited performance on other voice privacy tasks, emphasizing the need for further improvements.

• Report Guidelines for experiment design and conduction (Deliverable D1.1)
  C. Michel, L. Lardy, H. El Kechai, P. Dessus, S. Cojean and D. Vaufreydaz
  August 2024
   HAL[BibTeX][Abstract]

  @techreport{michel:hal-04753916,
    title = {{Guidelines for experiment design and conduction (Deliverable D1.1)}},
    author = {Michel, Christine and Lardy, Laurent and El Kechai, Hassina and Dessus, Philippe and Cojean, Salom{\'e} and Vaufreydaz, Dominique},
    hal_version = {v1},
    hal_id = {hal-04753916},
    keywords = {Student engagement ; Measures of student engagement ; Computer-based measures of student engagement},
    month = {August},
    year = {2024},
    institution = {{Universit{\'e} de Poitiers}},
    url = {https://hal.science/hal-04753916},
    abstract = {This report presents an in-depth review of the main theoretical models and methods for measuring student engagement in the educational context. The first part describes and compares the theoretical approaches proposed by several scholars (Astin, Skinner, and Fredricks). The second part takes stock of all existing means of collecting empirical data on engagement, manually with self-administered questionnaires, observations by teachers and observations by actors outside the learning situation, and automatically with behavioral analysis methods. The third part presents the experiments that we plan to carry out as part of the TALISMAN project.},
  }

  This report presents an in-depth review of the main theoretical models and methods for measuring student engagement in the educational context. The first part describes and compares the theoretical approaches proposed by several scholars (Astin, Skinner, and Fredricks). The second part takes stock of all existing means of collecting empirical data on engagement, manually with self-administered questionnaires, observations by teachers and observations by actors outside the learning situation, and automatically with behavioral analysis methods. The third part presents the experiments that we plan to carry out as part of the TALISMAN project.

• Proceedings AIED ethics, a managerial perspective
  E. Hoareau, S. Amer-Yahia and P. Dessus
  29e conférence de l’Association Information et Management (AIM), Montpellier, France, May 2024
   PDF HAL[BibTeX][Abstract]

  @inproceedings{hoareau:hal-04702418,
    title = {{AIED ethics, a managerial perspective}},
    author = {Hoareau, Emilie and Amer-Yahia, Sihem and Dessus, Philippe},
    booktitle = {{29e conf{\'e}rence de l'Association Information et Management (AIM)}},
    hal_version = {v1},
    hal_id = {hal-04702418},
    pdf = {https://hal.univ-grenoble-alpes.fr/hal-04702418v1/file/AIM_2024_AIED.pdf},
    keywords = {Case study ; Values ; Value Sensitive Design ; Education ; Artificial Intelligence ; Valeurs ; Value Sensitive Design ; {\'E}tude de cas ; {\'E}ducation ; Intelligence Artificielle},
    month = {May},
    year = {2024},
    address = {Montpellier, France},
    url = {https://hal.univ-grenoble-alpes.fr/hal-04702418},
    abstract = {This research in progress aims to address how values are integrated into Artificial Intelligence Education systems. Recent research points out ethical issues associated with Artificial Intelligence in Education (AIED). While existing studies are based on opinion experts, e.g. researchers on AI in Education (AIED), we take a manager’s perspective. Doing this, we refer to the Value Sensitive Design (VSD) approach to address the following question: “How values are integrated in AIED systems from a manager's perspective?”. We applied the case study method to seven French educational platforms. We already made the first data collection to obtain an overview of each platform. In a second phase, not yet launched, we plan to study in detail the design process of the AIED project of a few selected platforms. The preliminary results highlight the French landscape of AIED systems and the predominance of researchers as managers responsible for educational platforms.},
  }

  This research in progress aims to address how values are integrated into Artificial Intelligence Education systems. Recent research points out ethical issues associated with Artificial Intelligence in Education (AIED). While existing studies are based on opinion experts, e.g. researchers on AI in Education (AIED), we take a manager’s perspective. Doing this, we refer to the Value Sensitive Design (VSD) approach to address the following question: “How values are integrated in AIED systems from a manager's perspective?”. We applied the case study method to seven French educational platforms. We already made the first data collection to obtain an overview of each platform. In a second phase, not yet launched, we plan to study in detail the design process of the AIED project of a few selected platforms. The preliminary results highlight the French landscape of AIED systems and the predominance of researchers as managers responsible for educational platforms.