Publication details

DZEMUj: A Tool for Mining in e-Learning Tests. Description and Experience



Year of publication 2008
Type Article in Proceedings
Conference Proceedings of the 7th European Conference on eLearning ECEL
MU Faculty or unit

Faculty of Informatics

Field Informatics
Keywords data mining; e-learning; classification; visualization
Description We introduce DZEMUj, a system for mining in e-learning data, namely in electronic tests and DIA, DZEMUj Intelligent Assistant. DZEMUj farther extends capabilities of the elearning module of the Information system of Masaryk University and offers a set of tools for data analysis. DZEMUj enables to find the most difficult and/or the easiest test queries, to discover associations between answers and also between behaviour of students. We shortly describe data preparation, namely data transformation and data pre-processing. Then we focus on knowledge discovery and knowledge visualization - a scatter plot, RadViz and frequent patterns. DZEMUj has been testing on data from the e-learning module of Information System of Masaryk University since January 2008. DZEMUj is quite efficient. For 507 students, 80 different questions, 10 questions in a student test, the analysis finished in less then 1 minute. DZEMUj is implemented in python, java and R. We conclude this part with evaluation of DZEMUj. Then DIA, an intelligent assistant for DZEMUj is described.

You are running an old browser version. We recommend updating your browser to its latest version.

More info