FIT

Learning Feedback in Intelligent Tutoring Systems

  • Barbara Hammer (Supervisor-Bielefeld)
  • Bassam Mokbel 
  • Niels Pinkwart (Supervisor-Berlin)
  • Sebastian Groß
Term: March 2012 - March 2015
Research Area: D 

Abstract

Since about 1990, intelligent tutoring systems (ITS) have been getting more and more popular. Designing an ITS usually requires precise models of the underlying domain as well as of how a human tutor would respond to student mistakes. As such, the  applicability of ITSs is typically restricted to well-defined domains where such a formalization is possible, and large scale applications where development costs do not play a signicant role. For ill-defined domains, human tutors still by far outperform the performance of ITSs, or the latter are not applicable at all. The goal of the FIT project is to develop novel ITS methods which extend the applicability of ITS systems to ill-defined domains by means of machine learning techniques which can autonomously infer structures and feedback options from given data (e.g., student solutions). For this purpose, prototypebased methods and recent developments for general non-vectorial data structures will be extended such that they allow to simultaneously structure solution spaces, learn metrics for structures, align student solutions with clusters of other solutions, and infer appropriate feedback based thereon. The adaptation mechanisms will be developed in fully unsupervised scenarios or settings with only partial feedback to take into account the requirements for ITSs in ill-defined domains.

Research Questions and Methods

Details are provided at the SPP (Schwerpunkt-Programm) web-page about Autonomous Learning.

Outcomes

During the first two years of the project's duration, several milestones have been reached: First, user studies to investigate different feedback mechanisms provided the justification to develop a general concept for feedback provision in ill-defined domains. Next, the definition of a universal, domain-independent structural representation for solutions,along with the design and implementation of an appropriate software infrastructure, paved the way to process student solutions from various domains and react to students' feedback requests in real time. To ensure meaningful feedback, different structural similarity measures have been investigated and compared in terms of their suitability to reproduce syntactic and semantic relationships between solutions. Another crucial cornerstone was to establish a general mathematical foundation to transfer well-known prototype-based machine learning schemes to arbitrary structural similarity metrics. This opens the way for prototype-based clustering and classification on sets of solutions which are represented by the aforementioned similarity measures. In the most recent contributions, the first successful steps towards an autonomous learning of metric parameters have been taken, and first promising results have been accepted for publication in the near future.

Publications

Adaptive distance measures for sequential data

Mokbel B, Paaßen B, Hammer B (2014)
In: ESANN, 22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Verleysen M (Ed); Bruges, Belgium: i6doc.com: 265–270.
Conference Proceeding / Paper | Published | Quality Controlled | English

Link: http://pub.uni-bielefeld.de/publication/2673554
 

Learning vector quantization for (dis-)similarities

Hammer B, Hofmann D, Schleif F-M, Zhu X (2014)
NeuroComputing 131: 43–51.
Journal Article | Published | Quality Controlled | English

Link: http://pub.uni-bielefeld.de/publication/2615730
 

Towards Providing Feedback to Students in Absence of Formalized Domain Models

Gross S, Mokbel B, Hammer B, Pinkwart N (2013)
In: AIED. : 644–648.
Conference Proceeding / Paper | Published | Quality Controlled | English

Link: http://pub.uni-bielefeld.de/publication/2625207
 

Towards a Domain-Independent ITS Middleware Architecture

Gross S, Mokbel B, Hammer B, Pinkwart N (2013)
In: 2013 IEEE 13th International Conference on Advanced Learning Technologies. : 408–409.
Conference Proceeding / Paper | Published | Quality Controlled | English

Link: http://pub.uni-bielefeld.de/publication/2670686
 

How to Quantitatively Compare Data Dissimilarities for Unsupervised Machine Learning?

Mokbel B, Gross S, Lux M, Pinkwart N, Hammer B (2012)
In: Artificial Neural Networks in Pattern Recognition. Mana N, Schwenker F, Trentin E (Eds);7477 Springer Berlin Heidelberg: 1–13.
Conference Proceeding / Paper | Published | Quality Controlled | English

Link: http://pub.uni-bielefeld.de/publication/2536426
 

Cluster based feedback provision strategies in intelligent tutoring systems

Gross S, Zhu X, Hammer B, Pinkwart N (2012)
In: Proceedings of the 11th international conference on Intelligent Tutoring Systems. Berlin, Heidelberg: Springer-Verlag: 699–700.
Conference Proceeding / Paper | Published | Quality Controlled | English

Link: http://pub.uni-bielefeld.de/publication/2536437
 

Feedback Provision Strategies in Intelligent Tutoring Systems Based on Clustered Solution Spaces

Gross S, Mokbel B, Hammer B, Pinkwart N (2012)
In: DeLFI 2012: Die 10. e-Learning Fachtagung Informatik. Desel J, Haake JM, Spannagel C (Eds); Hagen, Germany: Köllen: 27–38.
Conference Proceeding / Paper | Published | Quality Controlled | English

Link: http://pub.uni-bielefeld.de/publication/2536444
 

Domain-Independent Proximity Measures in Intelligent Tutoring Systems

Mokbel B, Gross S, Paaßen B, Pinkwart N, Hammer B (2013)
In: Proceedings of the 6th International Conference on Educational Data Mining (EDM). D'Mello SK, Calvo RA, Olney A (Eds);: 334–335.
Conference Proceeding / Paper | Published | Quality Controlled | English

Link: http://pub.uni-bielefeld.de/publication/2625185