A Conceptual Educational Data Mining Model for Supporting Self-Regulated Learning in Online Learning Environments

A Conceptual Educational Data Mining Model for Supporting Self-Regulated Learning in Online Learning Environments

Eric Araka (Technical University of Kenya, Kenya), Robert Oboko (University of Nairobi, Kenya), Elizaphan Maina (Kenyatta University, Kenya) and Rhoda K. Gitonga (Kenyatta University, Kenya)
DOI: 10.4018/978-1-7998-4739-7.ch016
OnDemand PDF Download:
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Self-regulated learning is attracting tremendous researches from various communities such as information communication technology. Recent studies have greatly contributed to the domain knowledge that the use self-regulatory skills enhance academic performance. Despite these developments in SRL, our understanding on the tools and instruments to measure SRL in online learning environments is limited as the use of traditional tools developed for face-to-face classroom settings are still used to measure SRL on e-learning systems. Modern learning management systems (LMS) allow storage of datasets on student activities. Subsequently, it is now possible to use Educational Data Mining to extract learner patterns which can be used to support SRL. This chapter discusses the current tools for measuring and promoting SRL on e-learning platforms and a conceptual model grounded on educational data mining for implementation as a solution to promoting SRL strategies.
Chapter Preview
Top

Introduction

With increased adoption of online learning environments by most institutions of higher learning to offer online courses, investigating how students’ behavior in online courses is increasingly becoming important. Online learning environments lack the face-to-face instructor interactions that students in the traditional classroom setups where attendance, engagement, motivation and performance for students are monitored by lecturers. Monitoring the levels of engagement for online learners therefore is only possible through making inferences from the use of log data using machine learning algorithms. The analyses can then be used by instructors and educators to make policies that will enable early interventions for online learners whose degree of engagement is often lower compared to that of traditional classroom setup (Hussain, Zhu, Zhang, & Abidi, 2018). Educational Data Mining and Learning Analytics fields have become extremely valuable for decision makers in institutions of learning. Educational Data Mining and learning analytics provide opportunities of exploring complex datasets offers the potential to explore huge datasets stored in various educational environments such as Learning Management Systems (LMS), Web Based Training System (WBT-System) and Massive Open Online Courses (MOOC) system with the intention of detecting patterns and insights that can used by decision makers in understanding learners and learning environment where learning and teaching occurs. EDM techniques can be applied on datasets from educational environments to determine online learning behavior of students. These computer based learning environments provide virtual platforms where learners interact with content through online learning systems.

Most institutions of higher learning are adopting e-learning for online courses or a support for the face-to-face sessions in blended learning approach so as to curb the challenge of large backlog of students to be admitted (Hadullo, Oboko, & Omwenga, 2018; Luna, Castro, & Romero, 2017; Vovides, Sanchez-Alonso, Mitropoulou, & Nickmans, 2007). As a result there is increased number of students undertaking e-learning courses, (Bogarín, Cerezo, & Romero, 2018; Broadbent & Poon, 2015; Hashemyolia et al., 2014).

Key Terms in this Chapter

Educational Data Mining (EDM): Educational data mining is defined as an approach of applying machine learning or data mining algorithms on log data generated from educational environments in order to understand learners and learning environments ( Romero, López, Luna, & Ventura, 2013 ).

Self-Regulated Learning (SRL) Measurements: Self-regulated Learning measurements refer to the techniques that are used to establish or identify the levels of SRL skills present in students ( Triquet et al., 2017 ).

Self-Regulated Learning (SRL): Self-regulated learning is a theory described a process through which a student can plan, monitor and evaluate his or her learning processes by employing appropriate strategies. The theory through a number of theoretical frameworks defines activities that learners to enable them take control of their own learning ( Pintrich & Zusho, 2002 ; Zimmerman, 1986 )

Learning Analytics (LA): Learning Analytics involves the integration and analysis of students’ virtual learning data from educational platforms for insights and patterns on how students engage their learning activities in online learning. The main purpose is support and guide students by providing interventions to improve on their undesirable learning behaviors hence reinforcing positive learning habits ( Lodge, Panadero, Broadbent, & De Barba, 2019 ).

Learning Management Systems: Learning Management Systems refers to web-based applications that are used by instructors to deliver learning materials and allow students to access the content and interact and obtain support during learning. Besides making it easier for administrative or instructional online learning staff to manage, organize and provide online courses they act as intermediaries between teachers and learners. They also allow learning to be tracked and reported to help LMS managers make better decisions ( Delen & Liew, 2016 ; Safsouf, Mansouri, & Poirier, 2020 ).

Self-Regulated Learning (SRL) Interventions: Self-regulated Learning interventions refer to learning activities stimulate the development of self-regulatory skills especially during or teaching ( Triquet, Peeters, & Lombaerts, 2017 ).

Complete Chapter List

Search this Book:
Reset