Exam Question Recommender System

  • Authors:

  • Hicham Hage;Esma Aïmeur

  • Affiliations:

  • Department of Computer Science and Operational Research, University of Montreal, {hagehich, aimeur}@iro.umontreal.ca;Department of Computer Science and Operational Research, University of Montreal, {hagehich, aimeur}@iro.umontreal.ca

  • Venue:
  • Proceedings of the 2005 conference on Artificial Intelligence in Education: Supporting Learning through Intelligent and Socially Informed Technology
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Although E-learning has advanced considerably in the last decade, some of its aspects, such as E-testing, are still in the development phase. Authoring tools and test banks for E-tests are becoming an integral and indispensable part of E-learning platforms, and with the implementation of E-learning standards, such as IMS QTI, E-testing material can be easily shared and reased across various platforms. With this extensive E-testing material and knowledge comes a new challenge: searching for and selecting the most adequate information. In this paper we propose using recommendation techniques to help a teacher search for and select questions from a shared and centralized IMS QTI-compliant question bank. Our solution, the Exam Question Recommender System, uses a hybrid, feature-augmentation, recommendation approach. The recommender system uses Content-Based and Knowledge-Based recommendation techniques, resorting to the use of a new heuristic function. The system also engages in collecting both implicit and explicit feedback from the user in order to improve on future recommendations.