Educational data mining in the academic setting: employing the data produced by blended learning to ameliorate the learning process
| Date | 23 December 2022 |
| Pages | 366-384 |
| DOI | https://doi.org/10.1108/DTA-06-2022-0252 |
| Published date | 23 December 2022 |
| Author | Konstantinos Chytas,Anastasios Tsolakidis,Evangelia Triperina,Christos Skourlas |
Educational data mining in the
academic setting: employing the
data produced by blended learning
to ameliorate the learning process
Konstantinos Chytas, Anastasios Tsolakidis, Evangelia
Triperina and Christos Skourlas
University of West Attica, Athens, Greece
Abstract
Purpose –The purpose of this paper is to introduce an interactive system that relies on the educational data
generated from the online Universities services to assess, correct and ameliorate the learning process for both
students and faculty.
Design/methodology/approach –In the presented research, data from the online services, provided by
a Greek University, prior, during and after the COVID-19 outbreak, are analyzed and utilized in order to
ameliorate the offered learning process and provide better quality services to the students. Moreover,
according to the learning paths, their presence online and their participation in the services of the
University, insights can be derived for their performance, so as to better support and assist them.
Findings –The system can deduce the future learning progression of each student, according to the past
and the current performance. As a direct consequence, the exploitation of the data can provide a road map for
the strategic planning of universities, can indicate how the learning process can be updated and amended,
both online and in person, as well as make the learning experience more essential, effective and efficient for
the students and aiding the professors to provide a more meaningful and to-the-point learning experience.
Originality/value –Nowadays,educational activities in academiaare strongly supportedby online services,
informationsystems and online educationalmaterials. The learning designin the academic setting is primarily
facilitated in the University premises. However, the exploitation ofthe contemporary technologies and
supportingmaterials that are availableonline can enrich and transformthe educational processand its results.
Keywords Educational data mining, Blended learning, Learning analytics, Online services, Knowledge
discovery, Information system
Paper type Research paper
1. Introduction
Capturing teaching performance in academia is essential for defining the level of the quality
of education provided by an academic unit. Furthermore, the performance in education is
one of the main criteria that define a high-quality University (Shahiri and Husain, 2015).
Apart from recording of the educational performance, the exploitation of the data
abundance derived from the use of online services and platforms for the facilitation of
e-learning can lead to the enhancement of the learning process and its outputs. As a direct
result, more successful curricula can be produced and the success rate of the students
following these educational programs can be ameliorated. In order for such insights to be
generated, all the available information that supports the learning process, which is created
and stored in the aforementioned systems, must be aggregated and analyzed.
Monitoring the performance of the students, as well as predicting students at risk,
including dropouts, exam failures, etc., is essential for the academic sector. The information
needed to be recorded comprises the participation records, their grades in assignments,
quizzes and exams, their interaction within the context of the course and the access to the
educational material. Based on the prior presence of the students in a course, their recorded
ThecurrentissueandfulltextarchiveofthisjournalisavailableonEmeraldInsightat:
https://www.emerald.com/insight/2514-9288.htm
366
Received 21 June 2022
Revised 10 November 2022
Accepted 25 November 2022
Data Technologies and
Applications
Vol. 57 No. 3, 2023
pp. 366-384
© Emerald Publishing Limited
2514-9288
DOI 10.1108/DTA-06-2022-0252
DTA
57,3
performance and estimates about their future performance, progress and risks can be
extracted using educational data mining. Apart from the enhancement of the outputs of the
teaching, the improvement of the educational process itself is of paramountimportance. The
data generatedfrom teaching can indicate the overallcourse performance, so it can be usedto
reveal the elementsthat led to the success of the educational process, as well as a hint for the
necessary corrective measures. So, following the learning analytics cycle (Clow, 2012), the
analysis of the data and the metrics can ultimately lead to informed and updated learning
design, which takes account not only the feedback from the students but also their actual
reception and understanding of the subjects taught during the course (Nguyen et al.,2022).
Capturing and trying to enhance the educational process benefits both students and
professors, and also the academic institution, which will be ultimately providing better
education. The data that are required to be accumulated in order to access the performance
of a course includes but is not limitedto the following metrics attendance percentage, total
engagement views for each type of learning material that is available through the course,
participation percentage, etc. These metrics are also referred to as course analytics.
Nowadays, the analytics of the courses are available through the educational online
services that are provided by the University and provide a valuable tool for the decision
makers and the instructors.
The need for services that utilize the rich and intensive data to the benefit of the involved
stakeholders and the University is imminent. Educational data mining is focused on
exploiting the data derived from educational systems (Bakhshinategh et al., 2018), using
data mining techniques to this specific type of dataset that come from educational
environments to address important educational questions (Romero and Ventura, 2013).
Educational datasets can be used to monitor the past and the current academic
performance and behavior of the students, as well as to predict their future performance
and behavior. The data can also be used to provide recommendations to the students based
on their learning pathways and to avoid undesirable behaviors to track their progress and
assess their success. Apart from the support that educational data mining (EDM) can
provide to the learners, it can also assist the instructors by providing the required
feedback about the learning process outputs. The information can be further exploited to
improve the learning process for both the instructors and the students. By consistently
capturing the indicators that define the level of success in a course, we can compare the
course performance through the years, as well as the students’performance. Among the
performance indicators that are used in EDM are the grades achieved in exams and
exercises, the number of times the web page of the course is accessed by the students
and the overall participation in the course. Moreover, the grade distribution and the course
performance of the student groups, the engagement of the students, the log data, the course
access and the course navigation are also considered as critical indicators of their
performance. Although there are several methods that use EDM and learning analytics to
improve the educational activities, during the COVID outbreak (Sáiz-Manzanares et al.,
2021;Karalar et al., 2021), we aim not only to maintain the students’retention but also to
ultimately utilize the valuable information gathered to propose enhancements in the
educational process based on the participation and collaboration patterns of the students
that lead to success. In this approach, the authors employ the knowledge derived from the
technological infrastructure of the University’s web services, especially during and after the
pandemic, to enhance the face-to-face educational process and its results. The main novelty
that the proposed approach introduces is that it relies on the data generated during the
outbreak, as well as after the lockdown caused by the COVID outbreak, and exploits the
data retrieved to enhance the current and the future educational outputs. Combining
Learning Management Systems (LMS) log files, teleconferencing system log files and
GitHub data, we are gaining a more concrete and complete view of the situation in
Educational
data mining in
academic
setting
367
Get this document and AI-powered insights with a free trial of vLex and Vincent AI
Get Started for FreeStart Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting