Adaptive Testing in Programming Courses Based on Educational Data Mining Techniques
Designers of student tests, often teachers, primarily rely on their experience and subjective perception of students when selecting test items, while devoting little time to analyse factual data about both students and test items. As a practical solution
- PDF / 800,963 Bytes
- 31 Pages / 439.37 x 666.142 pts Page_size
- 67 Downloads / 177 Views
Adaptive Testing in Programming Courses Based on Educational Data Mining Techniques Vladimir Ivancˇevic´, Marko Knezˇevic´, Bojan Pušic´ and Ivan Lukovic´
Abstract Designers of student tests, often teachers, primarily rely on their experience and subjective perception of students when selecting test items, while devoting little time to analyse factual data about both students and test items. As a practical solution to this common issue, we propose an approach to automatic test generation that acknowledges required areas of competence and matches the overall competence level of target students. The proposed approach, which is tailored to the testing practice in an introductory university course on programming, is based on the use of educational data mining. Data about students and test items are first evaluated using the predictive techniques of regression and classification, respectively, and then used to guide the test creation process. Besides a genetic algorithm that selects a test most suitable to the aforementioned criteria, we present a concept map of programming competencies and a method of estimating the test item difficulty.
Keywords Programming competencies Concept maps Classification of test items Genetic algorithms
Test creation
Abbreviations ARC C1
Area coverage Criterion1
V. Ivancˇevic´ (&) M. Knezˇevic´ B. Pušic´ I. Lukovic´ University of Novi Sad, Faculty of Technical Sciences, Trg Dositeja Obradovic´a 6, 21 000 Novi Sad, Serbia e-mail: [email protected] M. Knezˇevic´ e-mail: [email protected] B. Pušic´ e-mail: [email protected] I. Lukovic´ e-mail: [email protected]
A. Peña-Ayala (ed.), Educational Data Mining, Studies in Computational Intelligence 524, DOI: 10.1007/978-3-319-02738-8_10, Springer International Publishing Switzerland 2014
257
V. Ivancˇevic´ et al.
258
C2 CAT CBA CR DF DM EDM FIT FTS GA GC IC IRT M MAX MDF MF MGC MH MIN MT NDF NDFC OWL PAS PLADS PS PTS RA RDF SC SCR SD SDF SGC SK SPDF SVM TPS TS TSR WRST
Criterion2 Computerized adaptive testing Computer-based assessment Correct ratio Difficulty Data mining Educational data mining Fitness Faculty of Technical Sciences Genetic algorithm Generation count Item count Item response theory Mean Maximum Mean difficulty Mean fitness Max generation count Math Minimum Mean completion time Natural difficulty Natural difficulty category Web ontology language Past assignment Programming languages and data structures Population size Past test Random approach Resource description framework Student capacity Student capacity rank Standard deviation Standard deviation for fitness Student group capacity Skewness Specified difficulty Support vector machine Test pool size Test Test ratio Wilcoxon rank sum test
10
Adaptive Testing in Programming Courses
259
10.1 Introduction Computerized testing represents an area that has emerged together with the rising popularity of personal computers and their increased availability. With their introduction into schools and universities, a large number of students could be swift
Data Loading...
