Learning About Learning at Scale: Methodological Challenges and Recommendations

Frans van der Sluis; Tim van der Zee; Jasper Ginn

doi:10.1145/3051457.3051461

Learning About Learning at Scale: Methodological Challenges and Recommendations

Frans van der Sluis, Tim van der Zee, Jasper Ginn

8 Citationer (Scopus)

Abstract

Learning at scale opens up a new frontier to learn about learning. Massive Online Open Courses (MOOCs) and similar large-scale online learning platforms give an unprecedented view of learners' behavior whilst learning. In this paper, we argue that the abundance of data that results from such platforms not only brings novel opportunities to the study of learning, but also bears novel methodological challenges. We show that the resulting data comes with various challenges with respect to the granular, observational, and large nature of these data. Additionally, we discuss a series of potential solutions, such as sharing validated models and performing pre-registered confirmatory research. With these contributions, this paper aims to increase awareness and understanding of both the strengths and challenges of research on learning at scale.

Originalsprog	Udefineret/Ukendt
Titel	Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale
Antal sider	10
Udgivelsessted	New York, NY, USA
Forlag	ACM
Publikationsdato	12 apr. 2017
Sider	131-140
ISBN (Trykt)	978-1-4503-4450-0
DOI	https://doi.org/10.1145/3051457.3051461
Status	Udgivet - 12 apr. 2017
Udgivet eksternt	Ja

Navn	L@S '17

Emneord

behavioral traces, big data, learning analytics, online learning, research methodology, research validity

Adgang til dokumentet

10.1145/3051457.3051461

http://doi.acm.org/10.1145/3051457.3051461

Citationsformater

@inproceedings{297da20de91e46598391db43cd756dec,

title = "Learning About Learning at Scale: Methodological Challenges and Recommendations",

abstract = "Learning at scale opens up a new frontier to learn about learning. Massive Online Open Courses (MOOCs) and similar large-scale online learning platforms give an unprecedented view of learners' behavior whilst learning. In this paper, we argue that the abundance of data that results from such platforms not only brings novel opportunities to the study of learning, but also bears novel methodological challenges. We show that the resulting data comes with various challenges with respect to the granular, observational, and large nature of these data. Additionally, we discuss a series of potential solutions, such as sharing validated models and performing pre-registered confirmatory research. With these contributions, this paper aims to increase awareness and understanding of both the strengths and challenges of research on learning at scale.",

keywords = "behavioral traces, big data, learning analytics, online learning, research methodology, research validity",

author = "{van der Sluis}, Frans and {van der Zee}, Tim and Jasper Ginn",

year = "2017",

month = apr,

day = "12",

doi = "10.1145/3051457.3051461",

language = "Udefineret/Ukendt",

isbn = "978-1-4503-4450-0",

series = "L@S '17",

publisher = "ACM",

pages = "131--140",

booktitle = "Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale",

}

TY - GEN

T1 - Learning About Learning at Scale

T2 - Methodological Challenges and Recommendations

AU - van der Sluis, Frans

AU - van der Zee, Tim

AU - Ginn, Jasper

PY - 2017/4/12

Y1 - 2017/4/12

N2 - Learning at scale opens up a new frontier to learn about learning. Massive Online Open Courses (MOOCs) and similar large-scale online learning platforms give an unprecedented view of learners' behavior whilst learning. In this paper, we argue that the abundance of data that results from such platforms not only brings novel opportunities to the study of learning, but also bears novel methodological challenges. We show that the resulting data comes with various challenges with respect to the granular, observational, and large nature of these data. Additionally, we discuss a series of potential solutions, such as sharing validated models and performing pre-registered confirmatory research. With these contributions, this paper aims to increase awareness and understanding of both the strengths and challenges of research on learning at scale.

AB - Learning at scale opens up a new frontier to learn about learning. Massive Online Open Courses (MOOCs) and similar large-scale online learning platforms give an unprecedented view of learners' behavior whilst learning. In this paper, we argue that the abundance of data that results from such platforms not only brings novel opportunities to the study of learning, but also bears novel methodological challenges. We show that the resulting data comes with various challenges with respect to the granular, observational, and large nature of these data. Additionally, we discuss a series of potential solutions, such as sharing validated models and performing pre-registered confirmatory research. With these contributions, this paper aims to increase awareness and understanding of both the strengths and challenges of research on learning at scale.

KW - behavioral traces, big data, learning analytics, online learning, research methodology, research validity

U2 - 10.1145/3051457.3051461

DO - 10.1145/3051457.3051461

M3 - Konferencebidrag i proceedings

SN - 978-1-4503-4450-0

T3 - L@S '17

SP - 131

EP - 140

BT - Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale

PB - ACM

CY - New York, NY, USA

ER -