Dynamic computerized testlet-based test generation system by discrete PSO with partial course ontology

  • Authors:

  • Kun Hua Tsai;Tzone I. Wang;Tung Cheng Hsieh;Ti Kai Chiu;Ming Che Lee

  • Affiliations:

  • Department of Engineering Science, National Cheng Kung University, No. 1, Ta-Hsueh Road, Tainan 701, Taiwan, ROC;Department of Engineering Science, National Cheng Kung University, No. 1, Ta-Hsueh Road, Tainan 701, Taiwan, ROC;Department of Engineering Science, National Cheng Kung University, No. 1, Ta-Hsueh Road, Tainan 701, Taiwan, ROC;Department of Engineering Science, National Cheng Kung University, No. 1, Ta-Hsueh Road, Tainan 701, Taiwan, ROC;Department of Computer and Communication Engineering, Ming Chuan University, 5 De Ming Road, Gui Shan District, Taoyuan County 333, Taiwan, ROC

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2010

Quantified Score

Hi-index 12.05

Visualization

Abstract

For the majority of E-learning systems their important role is the electronic teachers who can assist students to learn and review courses enrolled. Unfortunately, an E-learning system does not resemble a teacher who can evaluate the current students' learning status by the immediate class observations and adjust his/her policy accordingly. Hence, to be able to dynamically compose tests to examine students' learning status and clear their confusions becomes an important issue. This paper argues that how to formalize test requirements dynamically and how to select suitable items effectively are two main challenges in the current researches of computerized test generation. Hence, this article proposed a novel approach that can compose suitable tests to easily and efficiently evaluate the learning statuses of students. The proposed approach obeys the Discrete Particle Swarm Optimization (DPSO) scheme and uses partial course ontology to generate tests according to the studied materials. Besides, it also harnesses the notion of testlets to construct testlet-based tests for students. In the experiments, the results show that the proposed approach can effectively formalize the tested concepts and their weights, and also generate the well-scrutinized test in accordance with the test requirements in the acceptable time.