Premium
Association analysis of moodle e‐tests in blended learning educational environment
Author(s) -
Dimić Gabrijela,
Predić Bratislav,
Rančić Dejan,
Petrović Vera,
Maček Nemanja,
Spalević Petar
Publication year - 2018
Publication title -
computer applications in engineering education
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.478
H-Index - 29
eISSN - 1099-0542
pISSN - 1061-3773
DOI - 10.1002/cae.21894
Subject(s) - association rule learning , computer science , association (psychology) , apriori algorithm , preprocessor , process (computing) , a priori and a posteriori , graphics , data pre processing , e learning , test (biology) , multimedia , machine learning , data mining , data science , artificial intelligence , the internet , world wide web , programming language , psychology , paleontology , philosophy , computer graphics (images) , epistemology , psychotherapist , biology
The paper suggests the implementation of association analysis for improving the process of e‐testing in blended learning environment. The research has been conducted using knowledge tests at the Computer Graphics Moodle Course. In the preprocessing phase, data matrices have been created and prepared for the process of discovering significant relationships and links between students' answers to the questions from preparatory tests and those for testing knowledge, the ways of doing, and achieved results. By implementing Apriori and Predictive Apriori algorithms, a great number of association rules has been discovered. Important and interesting rules have been singled out by implementing objective and subjective assessment measures. The examples of interesting rules, as well as discovered patterns in items' relationships, have also been presented. The contribution of the described case study is visible in providing important feedback which enables the teacher to get a better insight into the concepts of created tests and decide on how to make changes to improve testing.