DŽEMUj - dobývání znalostí z odpovědníků IS MU

BRIATKOVÁ, Mária, Zdeněk KEDAJ and Lubomír POPELÍNSKÝ. DŽEMUj - dobývání znalostí z odpovědníků IS MU (DŽEMUj - data mining in electronic tests in IS MU). In Sborník konference SCO 2008. Brno: PřF MU, 2008, 6 pp. ISBN 978-80-210-4613-9.

Basic information

Original name

DŽEMUj - dobývání znalostí z odpovědníků IS MU

Name (in English)

DŽEMUj - data mining in electronic tests in IS MU

Authors

BRIATKOVÁ, Mária (203 Czech Republic), Zdeněk KEDAJ (203 Czech Republic) and Lubomír POPELÍNSKÝ (203 Czech Republic, guarantor)

Edition

Brno, Sborník konference SCO 2008, 6 pp. 2008

Publisher

PřF MU

---

Other information

Language

Czech

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Czech Republic

Confidentiality degree

není předmětem státního či obchodního tajemství

RIV identification code

RIV/00216224:14330/08:00035056

Organization unit

Faculty of Informatics

ISBN

978-80-210-4613-9

Keywords in English

e-learning; electronic tests; machine learning; visualization

Tags

e-learning, electronic tests, machine learning, visualization

Tags

International impact, Reviewed

---

Abstract

V originále

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.

In English

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.