Sébastien Lallé

Postdoctoral Research Fellow, Department of Computer Science, The University of British Columbia

My research

My research focuses on modeling user's needs, abitilies and skills so that real-time detection of those individual characteristics can be used to dynamically support users in computer-supported activities. In particular I studied two types of complex systems:
(1) Intelligent Tutoring Systems in which feedback/hints can be provided to support learning, based on the real-time assessment of student mastery of skills
(2) Information Visualization (Infovis) in which adaptive interventions can be provided to help users learning an unfamiliar visualisation based for instance on their cognitive abilities. I have also been interested in leveraging eye tracking data in machine learning models to dynamically predict individual user characteristics.

Keywords:

  • Artificial intelligence in education
  • User and student modeling
  • User-adaptive systems
  • Machine learning
  • Educational data mining
  • Information visualisation
  • Eye tracking

Contact

Room 125
ICICS/CS Building 2366 Main Mall
Vancouver, B.C. V6T 1Z4 Canada

lalles * at * cs.ubc.ca

About me

Full CV in PDF

Appointments:

  • Postdoctoral Research Fellow: Department of Computer Science, The University of British Columbia, Vancouver, Canada (2014-)
  • PhD candidate in Computer Science: University of Grenoble. Grenoble, France (2010-2013)
  • Visiting PhD candidate: The Robotics Institute, Carnegie Mellon University. Pittsburgh, PA, USA (July-December 2012)

Degrees:

  • 2013: PhD Degree in Computer Science. University of Grenoble, France. [detail]
  • 2010: Master Degree in Computer Science. Joseph Fourier University, Grenoble, France.

Teaching:

  • Introduction to algorithmic, programming and multimedia. TA (Lecture: 16h; Lab sessions: 44h). Joseph Fourier University (2011, 2012)
  • Operating systems and programming environments. TA (Lecture: 16h; Lab sessions: 44h). Joseph Fourier University (2013)

Other:

  • Publicity chair, International Conference on Artificial Intelligence in Education 2015
  • best paper award, International Conference on Intelligent Virtual Agent 2016
  • Mitacs postdoctoral grant (Canada, 2015)
  • Explora'doc international mobility grant (France, 2012)
  • Rhone-Alpes PhD scholarship (France, 2010)

Publications

Journal papers:

  • UMUAI'16. Lallé, S., Conati, C., and Carenini, G. 2016. Prediction of Individual Learning Curves across Information Visualizations. User Modeling and User-Adapted Interaction 26, 4, pp. 307-345. [link]

Strictly refereed international conference papers:

  • AIED'17. Lallé, S., Taub, M., Mudrick, N., Conati, C., and Azevedo, R. 2017. The Impact of Student Individual Differences and Visual Attention to Pedagogical Agents during Learning with MetaTutor. In Proc. of the 18th International Conference on Artificial Intelligence in Education, pp. 149-161. Wuhan, China: Springer [link]
  • EDM'17. Lallé, S., Conati, C., Taub, M., Mudrick, N., and Azevedo, R. 2017. On the Influence on Learning of Student Compliance with Prompts Fostering Self-Regulated Learning. In Proc. of the 10th International Conference on Educational Data Mining, pp. 120-127. Wuhan, China: Springer [link]
  • IJCAI'17. Conati, C., Lallé, S., Rahman, M.A., and Toker, D. 2017. Further Results on Predicting Cognitive Abilities for Adaptive Visualizations. In Proc. of the 26th International Joint Conference on Artificial Intelligence, pp. 1568-1574. Melbourne, Australia: AAAI [link].
  • IUI'17. Toker, D., Lallé, S., and Conati, C. 2017. Pupillometry and Head Distance to the Screen to Predict Skill Acquisition During Information Visualization Tasks. In Proc. of the 22nd International Conference on Intelligent User Interfaces, pp. 221-231. Limassol, Cyprus: ACM. [link]
  • IVA'16. Lallé, S., Mudrick, N., Taub, M., Grafsgaard, J., Conati, C., and Azevedo, R. 2016. Impact of Individual Differences on Affective Reactions to Pedagogical Agents Scaffolding. In Proc. of the 16th International Conference on Intelligent Virtual Agents, pp. 269-282. Los Angeles, CA, USA: Springer [Best paper award - link].
  • IJCAI'16. Lallé, S., Conati, C., and Carenini, G. 2016. Predicting Confusion in Information Visualization from Eye Tracking and Interaction data. In Proc. of the 25th International Joint Conference on Artificial Intelligence, pp. 2529-2535. New York, NY, USA: AAAI Press. [link]
  • IUI'15. Lallé, S., Toker, D., Conati, C., and Carenini, G. 2015. Prediction of Users' Learning Curves for Adaptation while Using an Information Visualization. In Proc. of the 20th International Conference on Intelligent User Interfaces, pp. 357-368. Atlanta, GA, USA: ACM. [link]
  • AAAI'15. Conati, C., Carenini, G., Toker, D., and Lallé, S. 2015. Towards User-Adaptive Information Visualization. In Proc. of the 29th AAAI Conference on Artificial Intelligence, pp. 4100-4106. Austin, TX, USA: AAAI. [link]
  • AIED'13. Lallé, S., Mostow, J., Luengo, V., and Guin, N. 2013. Comparing Student Models in Different Formalisms by Predicting Their Impact on Help Success. In Proc. of the 16th International Conference on Artificial Intelligence in Education, pp. 161-170. Memphis, TN, USA: Springer. [Nominee for the best paper award - link]
  • ITS'12. Goel, G., Lallé, S., and Luengo, V. 2012. Fuzzy Logic Representation for Student Modelling. In Proc. of the 11th International Conference on Intelligent Tutoring Systems, pp. 428-433. Chania, Greece: Springer. [Short - link]

Strictly refereed conference papers (in French):

  • EIAH'13. Lallé, S., Luengo, V., and Guin, N. 2013. Assistance à la conception de techniques de diagnostic des connaissances. In Proc. of 6th Conference on "Environnements Informatiques pour l'Apprentissage Humain", pp. 203-214. Toulouse, France. [link]
  • TICE'12. Lallé, S., Luengo, V., and Guin, N. 2013. Méthodologie d'assistance pour la comparaison de techniques de diagnostic des connaissance. In Proc. of 8th Conference on "Technlogies de l'Information et de la Communication pour l'Enseignement", pp. 6-16. Lyon, France. [Nominee for the best paper award - link]
  • EGC'11. Lallé, S., and Luengo, V. 2011. Intégration de données haptiques brutes dans des systèmes experts de diagnostic des connaissances. In Proc. of 11th Conference on "Extraction et Gestion de Connaissance", pp. 599-610. Brest, France. [link]

Other publications:

  • UMAP'17-workshop. Lallé, S.. Conati, C., and Carenini. G. 2017. Impact of Individual Differences on User Experience with a Visualization Interface for Public Engagement. In Proc. of the 2nd International Workshop on Human Aspects in Adaptive and Personalized Interactive Environments (in conjunction with UMAP 2017). Bratislava, Slovakia: ACM. [Workshop, to appear]
  • STELLAR'13-workshop. Bouhineau, D., Lallé, S., Luengo, V., Mandran, N., Ortega, M., and Wajeman, C. 2013. Share data treatment and analysis processes inTechnology enhanced learning. In Workshop Data Analysis and Interpretation for Learning Environments, 2nd STELLARnet Alpine Rendez-Vous. Autrans, France. [Workshop - link]
  • AIED'13-poster. Lallé, S., Luengo, V., and Guin, N. 2013. Assistance in building student models using knowledge representation and machine learning. In Proc. of the 16th International Conference on Artificial Intelligence in Education, pp. 754-757. Memphis, TN, USA: Springer. [Poster - link]
  • EDM'11-poster. Lallé, S., and Luengo, V. 2011. Learning Parameters for a Knowledge Diagnostic Tools in Orthopedic Surgery. In Proc. of 4th International Conference on Educational Data Mining, pp. 369-370. Eindhoven, The Netherlands. [Poster - link]

Thesis:

  • Phd Thesis: Lallé, S. 2013-12-11. Assistance à la construction et à la comparaison de techniques de diagnostic des connaissances dans les Environnements Informatiques pour l’Apprentissage Humain. Université de Grenoble/University of Grenoble.
    Under the supervision of Vanda Luengo and Nathalie Guin. Jury: Marie-Christine Rousset, Michel Desmarais, Jean-Marc Labat, Sebastian Ventura, Nicolas Delestre. [link - talk]

Tools

EMDAT: Eye Movement Data Analysis Toolkit

Library in Python for processing eye gaze data. EMDAT can calculate a comprehensive list of eye gaze features for each user. Additionally, EMDAT has built-in mechanisms for data preprocessing and clean up which makes it a valuable toolkit for researchers.
    [Source code - User manual]

Online Operation-Word Task test

Online test to evaluate a user's verbal working memory, i.e., the ability to mentally store and retrieve verbal/textual information.
    [Link]