-
Title
-
Educational Data Mining and Learning Analytics
-
Abstract/Description
-
In recent years, the use of analytics and data mining – methodologies that extract useful and actionable information from large datasets – has become commonplace in science (i.e. Jing et al., 2018) and commerce (Erevelles et al., 2016; Wang et al., 2016). When applied to education, these approaches are referred to as learning analytics (LA) and educational data mining (EDM). This work now appears in specialized journals and conferences specifically dedicated to work in this area – the International Conference on Educational Data Mining, the International Learning Analytics and Knowledge Conference, the Journal of Educational Data Mining, and the Journal of Learning Analytics, as well as more general educational research journals. The impact of learning analytics has grown – adaptive learning platforms have grown considerably in their user bases (Ubell, 2019), dropout prediction has emerged in K-12 education at even greater scale than its earlier emergence in higher education (Coleman et al., 2019), and the widespread adoption of analytics and its use to enhance learning systems has rapidly scaled in countries where learning analytics was rare even when the previous volume of this Handbook was published (i.e. Cui et al., 2018; Alkhalisi, 2019).
In this chapter we’ll define LA and EDM and give many examples of how they have been used. For example, one can analyze the impact of the design of learning environment features on learner behavior (cf. Cheng et al., 2017; Harpstead et al., 2019); one can conduct fine‐grained, even second‐by‐second, analysis of phenomena that occur over long periods of time (Yeung & Yeung, 2018; Hutt et al., 2019a); one can study how differences between groups influence the impact of behaviors on outcomes
(cf. Karumbaiah et al., 2019); one can assess the impact that adaptive feedback has on subsequent learner behavior (Pardo et a., 2018); and one can study how individual behaviors impact the dynamics of groups (cf. Martinez‐Maldonado et al., 2017; Järvelä et al., 2019). The data used in these analyses has broadened beyond interactive learning
environment or learning management system data (i.e. Koedinger et al., 2010) to include multimodal sensor data (Blikstein & Worsley, 2016; Schneider & Radu, this volume) and a wide range of other information collected by schools and educational agencies (Bowers et al., 2010, 2019; Agasisti et al., 2019), from grade data, to disciplinary and attendance data, to principal and teacher employment data. In the sections that follow, we discuss how learning analytics can be used to increase the sophistication of models of learning, contributing both to theory and practice.
-
Date
-
2014
-
In publication
-
The Cambridge Handbook of the Learning Sciences
-
Editor
-
Sawyer, R. Keith
-
Series
-
Cambridge Handbooks in Psychology
-
Edition
-
2
-
Pages
-
253-272
-
Publisher
-
Cambridge University Press
-
Open access/full-text available
-
en
Yes
-
Peer reviewed
-
en
Yes
-
ISBN
-
978-1-139-51952-6
-
Citation
-
Baker, R., & Siemens, G. (2014). Educational Data Mining and Learning Analytics. In R. K. Sawyer (Ed.), The Cambridge Handbook of the Learning Sciences (2nd ed., pp. 253–272). Cambridge University Press. https://doi.org/10.1017/CBO9781139519526.016
-
Place
-
Cambridge
Comments
No comment yet! Be the first to add one!