Socialization and Language at School: An Opportunity and a Challenge for AI in the Exploitation of Massive Data

Aurélie Nardy,
Associate professor,
aurelie.nardy@univ-grenoble-alpes.fr

Website

 

DESCRIPTION

Technological advances in the collection of massive learner data offer a new opportunity to improve pupils' learning conditions, requiring the involvement of AI to enrich, analyze, and model this data. Using the DyLNet database, encompassing 2.5 years of preschool social and verbal interactions (children and adults), this project tackles 3 key challenges: dynamically visualizing social interaction networks, developing an automatic transcription tool for spontaneous child speech that enables the assessment of language development level, and modeling the dynamic network of interactions and its reciprocal influences with language development. This massive database offers a unique opportunity to develop AI-based analyses and tools that would enable a significant qualitative leap in understanding the mechanisms of early socialization and its link with language with the goal of reducing social and educational inequalities.

ACTIVITIES

The chair will recruit a PhD student who will develop tools usable by researchers in the field of Social Sciences and Humanities enabling dynamic visualization for exploring social interaction networks in a preschool setting.

The chair will also hire an 18-month postdoctoral researcher to extract relevant information for characterizing representative indicators of child language development and to implement them in a tool that both automatically transcribes children's speech and assesses their level of language development.

Finally, a 24-month postdoctoral researcher will be hired to work on the modelling of the dynamic network of school interactions and its reciprocal influences with language usage.

SELECTED LIST OF PUBLICATIONS

  • Blanch, R. (2023). BiVis: interactive and progressive visualization of billions (and counting) items. In proc. 19th IFIP TC13 International Conference (Interact 2023). https://doi.org/10.1007/978-3-031-42283-6_4

  • Blanch, R., Lecointre, A., Ortega, M., Roux, P. (2023). Visualisation de données spatio-temporelles : Étude sismologique du glacier d’Argentière. In actes des Journées Visu 2023. https://journee-visu.github.io/2023/submissions/Blanch_et_al.pdf

  • Coulange, S., Kato, T., Rossato, S., & Masperi, M. (2024). Enhancing language learners’ comprehensibility through automated analysis of pause positions and syllable prominence. Languages, 9(3), 78. https://doi.org/10.3390/languages9030078

  • Dai, S., Bouchet, H., Karsai, M., Chevrot, J.-P., Fleury, E., Nardy, A. (2022). Longitudinal data collection to follow social network and language development dynamics at preschool. Scientific Data, 9, Article 777. https://doi.org/10.1038/s41597-022-01756-x

  • Dai, S., Bouchet, H., Nardy, A., Fleury, E., Chevrot, J.-P., Karsai, M. (2020). Temporal social network reconstruction using wireless proximity sensors: model selection and consequences. EPJ Data Science, 9, Article 19. https://doi.org/10.1140/epjds/s13688-020-00237-8

  • Evain, S., Rossato, S., Portet, F. (2024). Unraveling spontaneous speech dimensions for cross-corpus ASR system evaluation for French. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 17165–17175, Torino, Italy. https://aclanthology.org/2024.lrec-main.1491.pdf

  • Havard, W. N., Govain, R., Gonçalves Teixeira, D., Lecouteux, B., Schang, E. (2024). Technologies de la parole et données de terrain : le cas du créole haïtien. In Actes de la 31ème Conférence sur le Traitement Automatique des Langues Naturelles, volume 1 : articles longs et prises de position, pages 686–694, Toulouse, France. ATALA and AFPC. https://aclanthology.org/2024.jeptalnrecital-taln.45.pdf

  • Mouchené, M., Blanch, R., Pathier, E., Montet, R., Thollard, F. (2024). InsarViz: an open source Python package for the interactive visualization of satellite SAR interferometry data. Journal of Open Source Software, 9(101), 6440. https://doi.org/10.21105/joss.06440

  • Parcollet, T., Nguyen, H., Evain, S., Boito, M. Z., Pupier, A., Mdhaffar, S., Le, H., Alisamir, S., Tomashenko, N., Dinarelli, M., Zhang, S., Allauzen, A., Coavoux, M., Esteve, Y., Rouvier, M., Goulian, J., Lecouteux, B., Portet, F., Rossato, S., Ringeval, F., Schwab, D., Besacier, L. (2024). LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech. Computer Speech & Language, 86, 101622. https://doi.org/10.1016/j.csl.2024.101622



    CHAIR PRESENTATION

SoLas

License:
Unless otherwise stated, all documents are shared under the Creative Commons BY-NC-ND 4.0 license.
You may view and share them for non-commercial purposes, without modification, and with appropriate credit to the authors.

Published on  August 20, 2025
Updated on August 21, 2025