392113 Intelligent Tutoring Systems (S) (WiSe 2024/2025)

Intelligent tutoring systems are intended to help students in learning skills by selecting the individually best fitting next learning task ('outer loop') and supporting the student within each task with feedback and hints ('inner loop'). An intelligent tutoring system has four crucial components:

• a domain model, formalizing all skills that should be learned, all existing learning tasks, and the connections between skills and tasks
• a learner model, estimating the amount of skill each student has already learned
• a pedagogical model, deciding on the best pedagogical action given learner model and domain model
• a user interface.

The seminar will cover pedagogical theory, architectures, and strategies for intelligent tutoring systems and discuss foundational works in the field.

In the exercises, students will learn to implement intelligent tutoring systems (as web pages with frontend and backend).

Teilnahmevoraussetzungen, notwendige Vorkenntnisse

Recommended prior knowledge:

• Introduction to Machine Learning OR Introduction to Data Mining
• Software Engineering
• Programming Knowledge in Python & HTML & Javascript

Literaturangaben

• VanLehn (2006): The Behavior of Tutoring Systems. https://www.public.asu.edu/~kvanlehn/Stringent/PDF/06IJAIED.pdf
• Sottilare, Graesser, Hu, Holden (2013): Design recommendations for intelligent tutoring systems: Volume 1-learner modeling. https://play.google.com/store/books/details?id=2leEBAAAQBAJ
• Kulik, Fletcher (2016): Effectiveness of intelligent tutoring systems: a meta-analytic review. https://doi.org/10.3102/0034654315581420
• Aleven (2016): Help helps, but only so much: Research on help seeking with intelligent tutoring systems. https://doi.org/10.1007/s40593-015-0089-1