Applying graph sampling methods on student model initialization in intelligent tutoring systems. Issue 4 (1st August 2016)

• Record Type: Journal Article
• Authors: Vištica, Marija; Grubišić, Ani; Žitko, Branko
• Editors: Hardaker, Glenn; Anderson, Greg
• Is Part Of: International journal of information and learning technology. Volume 33:Issue 4(2016)
• Publication Date: 2016-08-01
• Subjects: Education, Higher -- Data processing -- Periodicals; Education, Higher -- Computer networks -- Periodicals; Education, Higher -- Information technology -- Periodicals; 378.00285
• DOI: 10.1108/IJILT-03-2016-0011
• Languages: English
• ISSNs: 2056-4880

Abstract

Abstract : Purpose: In order to initialize a student model in intelligent tutoring systems, some form of initial knowledge test should be given to a student. Since we cannot include all domain knowledge in that initial test, a domain knowledge subset should be selected. Design/methodology/approach: In order to generate a knowledge sample that represents truly a certain domain knowledge, we can use sampling algorithms. In this paper, we present five sampling algorithms (Random Walk, Metropolis-Hastings Random Walk, Forest Fire, Snowball and Represent algorithm) and investigate which structural properties of the domain knowledge sample are preserved after sampling process is conducted. Findings: The samples that we got using these algorithms are compared and we have compared their cumulative node degree distributions, clustering coefficients and the length of the shortest paths in a sampled graph in order to conclude about the best one. Originality/value: This approach is original as we could not find any similar work that uses graph sampling methods for student modeling.