Exploring the Colombian digital divide using Moodle logs through supervised learning

Purpose This study aims to explore the digital divide between students living in metropolitan and non-metropolitan areas in the Antioquia region of Colombia. This is achieved by collecting data about student interactions from the Moodle learning management system (LMS), and subsequently applying sup...

Full description

Autores:
Tipo de recurso:
Article of journal
Fecha de publicación:
2021
Institución:
Universidad de Bogotá Jorge Tadeo Lozano
Repositorio:
Expeditio: repositorio UTadeo
Idioma:
eng
OAI Identifier:
oai:expeditiorepositorio.utadeo.edu.co:20.500.12010/28017
Acceso en línea:
https://www.emerald.com/insight/content/doi/10.1108/ITSE-03-2021-0052/full/html?skipTracking=true
http://hdl.handle.net/20.500.12010/28017
http://expeditiorepositorio.utadeo.edu.co
Palabra clave:
Behaviour
Modelling
Distance learning
Aprendizaje
Aptitud de aprendizaje
Educación en línea
Rights
License
Abierto (Texto Completo)
Description
Summary:Purpose This study aims to explore the digital divide between students living in metropolitan and non-metropolitan areas in the Antioquia region of Colombia. This is achieved by collecting data about student interactions from the Moodle learning management system (LMS), and subsequently applying supervised machine learning models to infer the gap between students in metropolitan and non-metropolitan areas. Design/methodology/approach This work uses the well-established Cross-Industry Standard Process for Data Mining methodology, which comprises six phases, viz., problem understanding, data understanding, data preparation, modelling, evaluation and implementation. In this case, student data was collected from the Moodle platform from the Antioquia campus of the UNAD distance learning university. Findings The digital divide is evident in the classification model when observing differences in variables such as the number of accesses to the LMS, the total time spent and the number of distinct IP addresses used, as well as the number of system modification events. Originality/value This study provides conclusions regarding the problems students in virtual education may face as a result of the digital divide in Colombia which have become increasingly visible since the implementation of machine learning methodologies on LMS such as Moodle. However, these practices may be replicated in any virtual educational context and furthermore be extended to enable personalisation of various aspects of the Moodle platform to meet the individual needs of students.