TY - JOUR
T1 - Analyzing the educational goals, problems and techniques used in educational big data research from 2010 to 2018
AU - Quadir, Benazir
N1 - Funding Information:
This work was supported by the National Science Council, Taiwan under project numbers MOST-107-2511-H-224-007-MY3 and MOST-106-2511-S-224-005-MY3. This work was also partially supported by Doctoral Foundation Project, Business School [grant number 4033/718011], Shandong University of Technology, China.
Publisher Copyright:
© 2020 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2022/7/4
Y1 - 2022/7/4
N2 - The purpose of this study is to review journal papers on educational big data research published from 2010 to 2018. A total of 143 papers were selected. The papers were characterized based on three dimensions: (a) educational goals; (b) educational problems addressed; and (c) big data analytical techniques used. A qualitative content analysis approach was conducted to develop a coding scheme for analyzing the selected papers. The results identified four types of educational goals, with a clear predominance of quality assurance. The identification of the most mentioned educational problems resulted in four main concerns: the lack of detecting student behavior modeling and waste of resources; inappropriate curricula and teaching strategies; oversights of quality assurance; and privacy and ethical issues. Concerning the most mentioned big data analytical techniques, the coding scheme revealed that the majority of the papers focused on the educational data mining technique followed by the learning analytics technique. The visual analytics technique was mentioned in a few papers. The results also indicated that the educational data mining technique is the most suitable technique to use for quality assurance and to provide potential solutions for the lack of detecting student behavior modeling and the waste of resources in institutions.
AB - The purpose of this study is to review journal papers on educational big data research published from 2010 to 2018. A total of 143 papers were selected. The papers were characterized based on three dimensions: (a) educational goals; (b) educational problems addressed; and (c) big data analytical techniques used. A qualitative content analysis approach was conducted to develop a coding scheme for analyzing the selected papers. The results identified four types of educational goals, with a clear predominance of quality assurance. The identification of the most mentioned educational problems resulted in four main concerns: the lack of detecting student behavior modeling and waste of resources; inappropriate curricula and teaching strategies; oversights of quality assurance; and privacy and ethical issues. Concerning the most mentioned big data analytical techniques, the coding scheme revealed that the majority of the papers focused on the educational data mining technique followed by the learning analytics technique. The visual analytics technique was mentioned in a few papers. The results also indicated that the educational data mining technique is the most suitable technique to use for quality assurance and to provide potential solutions for the lack of detecting student behavior modeling and the waste of resources in institutions.
KW - Educational goals
KW - educational big data
KW - educational data mining
KW - educational problems
KW - learning analytics meta-analysis
UR - http://www.scopus.com/inward/record.url?scp=85078825039&partnerID=8YFLogxK
U2 - https://doi.org/10.1080/10494820.2020.1712427
DO - https://doi.org/10.1080/10494820.2020.1712427
M3 - Article
AN - SCOPUS:85078825039
SN - 1049-4820
VL - 30
SP - 1539
EP - 1555
JO - Interactive Learning Environments
JF - Interactive Learning Environments
IS - 8
ER -