Online

ADS x AUAS Smart Education Lab: Intelligent Interaction in Education

Amsterdam Data Science (ADS) and the Smart Education Lab of Amsterdam University of Applied Sciences (AUAS) (part of the Centre of Expertise Applied AI) are joining forces for an online meetup. Expect inspiring talks with examples from primary, secondary and higher education on the theme of Intelligent Interaction. Let us know if you will be joining here!

 

This year it’s the third time that SURF, Nederlandse AI Coalitie | NL AIC, Nationaal Onderwijslab AI (NOLAI), Kennisnet and Special Interest Group AIED organise the Month of AI in June!

Location: Online – Use the following link to join the meetup – https://edu.nl/faucb

Programme
16:00 Walk-in, introduction & Welcome by Bert Bredeweg
16:05 Talk #1: Marco Kragten: Learning with Interactive Qualitative Representations
16:25 Discussion
16:35 Talk #2: Somaya Ben Allouch: Designing a Social Robotic for Math Learning
16:55 Discussion
17:05 Talk #3: Erwin Van Vliet: IguideME supporting self-regulated learning and academic achievement with personalised peer comparison feedback
17:25 Discussion
17:35 End

  • Moderator: Bert Bredeweg (Amsterdam University of Applied Sciences)
    Bio: He is professor of science education at the Amsterdam University of Applied Science (AUAS) and associate professor at the University of Amsterdam (UvA, Informatics Institute). His research concerns Artificial Intelligence in Education, particularly investigating how learners create knowledge and acquire skills, and how this can be supported using digital technology. Active learning (‘learning by doing’) is a continuous focus in his work. At the AUAS Bredeweg leads the Smart Education lab. Research topics of the lab include: interactive knowledge representations, learning analytics, computational thinking and game-based learning.
  • Talk #1 by Marco Kragten (Amsterdam University of Applied Sciences)
    Title: Learning with Interactive Qualitative Representations
    Abstract: The ‘Denker’-project (https://denker.nu/) focuses on investigating the effective use of interactive qualitative representations as a method for understanding systems among secondary school students. Interactive qualitative representations offer a means to describe system behavior without relying on precise quantitative information. These representations serve as executable models, enabling system simulations. The project has successfully developed more than 30 teaching activities that align directly with the current secondary education curriculum. Students interact with qualitative representations using the Dynalearn software (https://www.dynalearn.nl). Throughout the project, the software has been enhanced with multiple functions designed to support the interaction for both students and teachers. During the presentation, we will showcase examples of the developments and research conducted in recent years.
  • Talk #2 by Somaya Ben Allouch (University of Amsterdam, Amsterdam University of Applied Sciences)
    Title: Designing a Social Robotic for Math Learning
    Abstract: To benefit from the social capabilities of a robot math tutor, instead of being distracted by them, a novel approach is needed where the math task and the robot’s social behaviors are better intertwined. In this talk, prof. Ben Allouch (UvA & HvA) will present a part of the SOROCOVA study in which we present concrete design specifcations of how children can practice math via a personal conversation with a social robot and how the robot can scaffold instructions. We evaluated the designs with a three-session experimental user study. Participants got better at math over time when the robot scaffolded instructions. Furthermore, the robot felt more as a friend when it personalized the conversation.
  • Talk #3 by Erwin van Vliet (University of Amsterdam)
    Title: “IguideME: supporting self-regulated learning and academic achievement with personalised peer comparison feedback”
    Abstract: Learning data (e.g., from summative and formative tests) can be continuously collected and visualized via the LA dashboard “IguideME” that we have developed. Using AI, personalized peer comparison feedback can be provided to students, even in large-scale courses. Lecturers can use the dashboard as an “early warning system” to prevent dropout, but also to analyze and immediately adjust their course design. In this lecture, he will explain how IguideME works and how it can be applied in practice. Furthermore, he will present research data showing that IguideME improves self-regulated learning and academic performance.