Inferring Learning from Big Data

The Importance of a Transdisciplinary and Multidimensional Approach

Jason Lodge, Sakinah S.J. Alhadad, Melinda Lewis, Dragan Gašević

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

The use of big data in higher education has evolved rapidly with a focus on the practical application of new tools and methods for supporting learning. In this paper, we depart from the core emphasis on application and delve into a mostly neglected aspect of the big data conversation in higher education. Drawing on developments in cognate disciplines, we analyse the inherent difficulties in inferring the complex phenomenon that is learning from big datasets. This forms the basis of a discussion about the possibilities for systematic collaboration across different paradigms and disciplinary backgrounds in interpreting big data for enhancing learning. The aim of this paper is to provide the foundation for a research agenda, where differing conceptualisations of learning become a strength in interpreting patterns in big datasets, rather than a point of contention.
Original languageEnglish
Pages (from-to)385-400
Number of pages16
JournalTechnology, Knowledge and Learning
Volume22
Issue number3
Early online dateJul 2017
DOIs
Publication statusPublished - Oct 2017

Fingerprint

transdisciplinary
Education
Higher Education
learning
Contention
education
conversation
Paradigm
paradigm
Learning
Big data

Cite this

Lodge, Jason ; Alhadad, Sakinah S.J. ; Lewis, Melinda ; Gašević, Dragan. / Inferring Learning from Big Data : The Importance of a Transdisciplinary and Multidimensional Approach. In: Technology, Knowledge and Learning. 2017 ; Vol. 22, No. 3. pp. 385-400.
@article{441ff2d947194540ac9eb58d934a55d5,
title = "Inferring Learning from Big Data: The Importance of a Transdisciplinary and Multidimensional Approach",
abstract = "The use of big data in higher education has evolved rapidly with a focus on the practical application of new tools and methods for supporting learning. In this paper, we depart from the core emphasis on application and delve into a mostly neglected aspect of the big data conversation in higher education. Drawing on developments in cognate disciplines, we analyse the inherent difficulties in inferring the complex phenomenon that is learning from big datasets. This forms the basis of a discussion about the possibilities for systematic collaboration across different paradigms and disciplinary backgrounds in interpreting big data for enhancing learning. The aim of this paper is to provide the foundation for a research agenda, where differing conceptualisations of learning become a strength in interpreting patterns in big datasets, rather than a point of contention.",
keywords = "Learning analytics , Inference , Predictive modelling , Transdisciplinarity",
author = "Jason Lodge and Alhadad, {Sakinah S.J.} and Melinda Lewis and Dragan Gašević",
year = "2017",
month = "10",
doi = "10.1007/s10758-017-9330-3",
language = "English",
volume = "22",
pages = "385--400",
journal = "Technology, Knowledge and Learning",
issn = "2211-1662",
publisher = "Springer Science + Business Media",
number = "3",

}

Inferring Learning from Big Data : The Importance of a Transdisciplinary and Multidimensional Approach. / Lodge, Jason; Alhadad, Sakinah S.J.; Lewis, Melinda; Gašević, Dragan.

In: Technology, Knowledge and Learning, Vol. 22, No. 3, 10.2017, p. 385-400.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Inferring Learning from Big Data

T2 - The Importance of a Transdisciplinary and Multidimensional Approach

AU - Lodge, Jason

AU - Alhadad, Sakinah S.J.

AU - Lewis, Melinda

AU - Gašević, Dragan

PY - 2017/10

Y1 - 2017/10

N2 - The use of big data in higher education has evolved rapidly with a focus on the practical application of new tools and methods for supporting learning. In this paper, we depart from the core emphasis on application and delve into a mostly neglected aspect of the big data conversation in higher education. Drawing on developments in cognate disciplines, we analyse the inherent difficulties in inferring the complex phenomenon that is learning from big datasets. This forms the basis of a discussion about the possibilities for systematic collaboration across different paradigms and disciplinary backgrounds in interpreting big data for enhancing learning. The aim of this paper is to provide the foundation for a research agenda, where differing conceptualisations of learning become a strength in interpreting patterns in big datasets, rather than a point of contention.

AB - The use of big data in higher education has evolved rapidly with a focus on the practical application of new tools and methods for supporting learning. In this paper, we depart from the core emphasis on application and delve into a mostly neglected aspect of the big data conversation in higher education. Drawing on developments in cognate disciplines, we analyse the inherent difficulties in inferring the complex phenomenon that is learning from big datasets. This forms the basis of a discussion about the possibilities for systematic collaboration across different paradigms and disciplinary backgrounds in interpreting big data for enhancing learning. The aim of this paper is to provide the foundation for a research agenda, where differing conceptualisations of learning become a strength in interpreting patterns in big datasets, rather than a point of contention.

KW - Learning analytics

KW - Inference

KW - Predictive modelling

KW - Transdisciplinarity

UR - http://www.scopus.com/inward/record.url?scp=85025452120&partnerID=8YFLogxK

U2 - 10.1007/s10758-017-9330-3

DO - 10.1007/s10758-017-9330-3

M3 - Article

VL - 22

SP - 385

EP - 400

JO - Technology, Knowledge and Learning

JF - Technology, Knowledge and Learning

SN - 2211-1662

IS - 3

ER -