Multilevel clustering and association rule mining for learners profiles analysis
Educational Data Mining is concerned with developing
methods for exploring data that come from educational domains,
and using those methods to better understand learner, and how
they interact with those environments.
In this research, we benefit from a new preprocessing approach
applied to Moodle platform [1] [2] in order to apply clustering
and association rule mining techniques to analyze learners
behaviors, to help in learning evaluation, and to enhance the
structure of a given SCORM content.
We adopted the feature selection process and multilevel
clustering that allowed us to confirm the importance of these new
data preprocessing methods and to validate the usefulness of the
attributes describing the learners\' interactions with the SCORM
content pertaining to learners profiles detection. We also
benefited from this approach as we sought to find possible
relationships between the different parts of the relevant content
and to help the teacher/ tutor to evaluate the structure of such
content.
Keywords: Educational data mining; Moodle; preprocessing; clustering; association rule mining; learning profiles
Download Full-Text
ABOUT THE AUTHORS
Nawal Sael
Laboratory of Information Technology and Modelization, Faculty of Science Ben M’sik
Abdelaziz Marzak
Laboratory of Information Technology and Modelization, Faculty of Science Ben M’sik
Hicham Behja
Laboratory of Command and Control and Production Systems, National High School of Art and Craft
Nawal Sael
Laboratory of Information Technology and Modelization, Faculty of Science Ben M’sik
Abdelaziz Marzak
Laboratory of Information Technology and Modelization, Faculty of Science Ben M’sik
Hicham Behja
Laboratory of Command and Control and Production Systems, National High School of Art and Craft