Towards real-time analytics in MOOCs

Daniel T. Seaton, Yoav Bergner, Isaac Chuang, Pitor Mitros, David E. Pritchard

Research output: Contribution to journalArticle

Abstract

Massive open online courses (MOOCs) collect essentially complete records of all student interactions in a self-contained learning environment, with the benefit of large sample sizes. Building on our data mining of the first course in MITx (now edX) we demonstrate ways to analyze data to illustrate important issues in the course: how to distinguish browsers from certificate-earners, which resources were accessed the most and how much time was allocated by certificate-earners. Each topic is addressed via appropriate displays that, in future courses, can be updated in real time. Furthermore, we stress that analytics can provide useful information to teachers, to resource creators (authors), and to members of organizations trying to improve their MOOCs.

Original languageEnglish (US)
JournalCEUR Workshop Proceedings
Volume985
StatePublished - 2013

Fingerprint

Data mining
Display devices
Students

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Seaton, D. T., Bergner, Y., Chuang, I., Mitros, P., & Pritchard, D. E. (2013). Towards real-time analytics in MOOCs. CEUR Workshop Proceedings, 985.

Towards real-time analytics in MOOCs. / Seaton, Daniel T.; Bergner, Yoav; Chuang, Isaac; Mitros, Pitor; Pritchard, David E.

In: CEUR Workshop Proceedings, Vol. 985, 2013.

Research output: Contribution to journalArticle

Seaton, DT, Bergner, Y, Chuang, I, Mitros, P & Pritchard, DE 2013, 'Towards real-time analytics in MOOCs', CEUR Workshop Proceedings, vol. 985.
Seaton DT, Bergner Y, Chuang I, Mitros P, Pritchard DE. Towards real-time analytics in MOOCs. CEUR Workshop Proceedings. 2013;985.
Seaton, Daniel T. ; Bergner, Yoav ; Chuang, Isaac ; Mitros, Pitor ; Pritchard, David E. / Towards real-time analytics in MOOCs. In: CEUR Workshop Proceedings. 2013 ; Vol. 985.
@article{7c675acb3cb24f93b10054f215528c2c,
title = "Towards real-time analytics in MOOCs",
abstract = "Massive open online courses (MOOCs) collect essentially complete records of all student interactions in a self-contained learning environment, with the benefit of large sample sizes. Building on our data mining of the first course in MITx (now edX) we demonstrate ways to analyze data to illustrate important issues in the course: how to distinguish browsers from certificate-earners, which resources were accessed the most and how much time was allocated by certificate-earners. Each topic is addressed via appropriate displays that, in future courses, can be updated in real time. Furthermore, we stress that analytics can provide useful information to teachers, to resource creators (authors), and to members of organizations trying to improve their MOOCs.",
author = "Seaton, {Daniel T.} and Yoav Bergner and Isaac Chuang and Pitor Mitros and Pritchard, {David E.}",
year = "2013",
language = "English (US)",
volume = "985",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

TY - JOUR

T1 - Towards real-time analytics in MOOCs

AU - Seaton, Daniel T.

AU - Bergner, Yoav

AU - Chuang, Isaac

AU - Mitros, Pitor

AU - Pritchard, David E.

PY - 2013

Y1 - 2013

N2 - Massive open online courses (MOOCs) collect essentially complete records of all student interactions in a self-contained learning environment, with the benefit of large sample sizes. Building on our data mining of the first course in MITx (now edX) we demonstrate ways to analyze data to illustrate important issues in the course: how to distinguish browsers from certificate-earners, which resources were accessed the most and how much time was allocated by certificate-earners. Each topic is addressed via appropriate displays that, in future courses, can be updated in real time. Furthermore, we stress that analytics can provide useful information to teachers, to resource creators (authors), and to members of organizations trying to improve their MOOCs.

AB - Massive open online courses (MOOCs) collect essentially complete records of all student interactions in a self-contained learning environment, with the benefit of large sample sizes. Building on our data mining of the first course in MITx (now edX) we demonstrate ways to analyze data to illustrate important issues in the course: how to distinguish browsers from certificate-earners, which resources were accessed the most and how much time was allocated by certificate-earners. Each topic is addressed via appropriate displays that, in future courses, can be updated in real time. Furthermore, we stress that analytics can provide useful information to teachers, to resource creators (authors), and to members of organizations trying to improve their MOOCs.

UR - http://www.scopus.com/inward/record.url?scp=84922569116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922569116&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84922569116

VL - 985

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -