Beyond Prediction: First Steps Toward Automatic Intervention in MOOC Student Stopout

8 Pages Posted: 29 May 2015

See all articles by Jacob Whitehill

Jacob Whitehill

Harvard University

Joseph Williams

National University of Singapore

Glenn Lopez

Harvard University

Cody Coleman

Massachusetts Institute of Technology (MIT) - Electrical Engineering and Computer Science

Justin Reich

Massachusetts Institute of Technology (MIT) - Office of Digital Learning

Date Written: April 23, 2015

Abstract

High attrition rates in massive open online courses (MOOCs) have motivated growing interest in the automatic detection of student "stopout". Stopout classifiers can be used to orchestrate an intervention before students quit, and to survey students dynamically about why they ceased participation. In this paper we expand on existing stop-out detection research by (1) exploring important elements of classifier design such as generalizability to new courses; (2) developing a novel framework inspired by control theory for how to use a classifier's outputs to make intelligent decisions; and (3) presenting results from a "dynamic survey intervention" conducted on 2 HarvardX MOOCs, containing over 40,000 students, in early 2015. Our results suggest that surveying students based on an automatic stopout classifier achieves higher response rates compared to traditional post-course surveys, and may boost students' propensity to "come back" into the course.

Keywords: massive open online courses, machine learning, stopout prediction

Suggested Citation

Whitehill, Jacob and Williams, Joseph and Lopez, Glenn and Coleman, Cody and Reich, Justin, Beyond Prediction: First Steps Toward Automatic Intervention in MOOC Student Stopout (April 23, 2015). Available at SSRN: https://ssrn.com/abstract=2611750 or http://dx.doi.org/10.2139/ssrn.2611750

Jacob Whitehill (Contact Author)

Harvard University ( email )

1875 Cambridge Street
Cambridge, MA 02138
United States

Joseph Williams

National University of Singapore ( email )

Singapore

HOME PAGE: http://www.josephjaywilliams.com/

Glenn Lopez

Harvard University ( email )

1875 Cambridge Street
Cambridge, MA 02138
United States

Cody Coleman

Massachusetts Institute of Technology (MIT) - Electrical Engineering and Computer Science ( email )

77 Massachusetts Avenue
Cambridge, MA 02139-4307
United States

Justin Reich

Massachusetts Institute of Technology (MIT) - Office of Digital Learning ( email )

77 Massachusetts Avenue
Cambridge, MA 02139
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
320
Abstract Views
1,239
rank
92,718
PlumX Metrics