Analysing Moodle learning behaviour about virtual patients
Xu, Menglin (2017)
2017
Tietojenkäsittelytieteiden tutkinto-ohjelma - Degree Programme in Computer Sciences
Luonnontieteiden tiedekunta - Faculty of Natural Sciences
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2017-06-14
Julkaisun pysyvä osoite on
http://urn.fi/URN:NBN:fi:uta-201706202067
http://urn.fi/URN:NBN:fi:uta-201706202067
Tiivistelmä
With the development of Internet, online learning management systems (LMSs) have been used widely for providing teaching platforms. The vast quantities of data that LMSs generate daily are difficult to manage manually. Thus, educational data mining (EDM) is applied to solve this problem.
In this thesis, EDM is applied on Moodle log data of a medical course. This course was arranged by problem-based learning (PBL) method, which uses virtual patients (VPs) as a problem, to improve students' diagnostic skills. The aim of this thesis is to analyse Moodle learning behaviour related to the usage of VPs and implement a set of Python algorithms to handle such kind of data. There are two ways are utilised to analyse Moodle log data by EDM: applying data mining techniques and implementing Python scripts. The techniques applied on the first way are attribute weighting and generalized sequential patterns (GSP), while the second way provides Python algorithms about extracting frequencies, sessions, and relationship tables.
This thesis shows learning behaviour records and patterns about the usage of each VP. In addition, it gives information about the overall usage of different kinds of activities and resources that Moodle offers. Moreover, Python algorithms implemented in this thesis provide tools to extract frequencies, sessions, and relationship tables of Moodle log data for further research.
In this thesis, EDM is applied on Moodle log data of a medical course. This course was arranged by problem-based learning (PBL) method, which uses virtual patients (VPs) as a problem, to improve students' diagnostic skills. The aim of this thesis is to analyse Moodle learning behaviour related to the usage of VPs and implement a set of Python algorithms to handle such kind of data. There are two ways are utilised to analyse Moodle log data by EDM: applying data mining techniques and implementing Python scripts. The techniques applied on the first way are attribute weighting and generalized sequential patterns (GSP), while the second way provides Python algorithms about extracting frequencies, sessions, and relationship tables.
This thesis shows learning behaviour records and patterns about the usage of each VP. In addition, it gives information about the overall usage of different kinds of activities and resources that Moodle offers. Moreover, Python algorithms implemented in this thesis provide tools to extract frequencies, sessions, and relationship tables of Moodle log data for further research.