Comparing attrition prediction in FutureLearn and edX MOOCs

Ruth Cobos; Adriana Wilde; Ed Zaluska

Comparing attrition prediction in FutureLearn and edX MOOCs

Ruth Cobos, Adriana Wilde, Ed Zaluska

School of Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

There are a number of similarities and differences between FutureLearn MOOCs and those offered by other platforms, such as edX. In this research we compare the results of applying machine learning algorithms to predict course attrition for two case studies using datasets from a selected FutureLearn MOOC and an edX MOOC of comparable structure and themes. For each we have computed a number of attributes in a pre-processing stage from the raw data available in each course. Following this, we applied several machine learning algorithms on the pre-processed data to predict attrition levels for each course. The analysis suggests that the attribute selection varies in each scenario, which also impacts on the behaviour of the predicting algorithms.

Original language	English
Number of pages	9
Publication status	Published - 13 Mar 2017
Event	FutureLearn Workshop in Learning Analytics and Knowledge 2017 (LAK17) - Simon Fraser University, Vancouver, Canada Duration: 13 Mar 2017 → 17 Mar 2017 Conference number: 7 https://sites.google.com/site/lak17flworkshop/

Workshop

Workshop	FutureLearn Workshop in Learning Analytics and Knowledge 2017 (LAK17)
Abbreviated title	LAK17
Country/Territory	Canada
City	Vancouver
Period	13/03/17 → 17/03/17
Internet address	https://sites.google.com/site/lak17flworkshop/

Keywords

MOOCs
Predictive model
Learning analytics
Attribute selection
FutureLearn
edX

Access to Document

FL_LAK_rc_agw_ejz2
Copyright 2017 the Authors.
Accepted author manuscript, 360 KB

Cite this

@conference{63a78dc4580c4ef9b6eb749b5458a807,

title = "Comparing attrition prediction in FutureLearn and edX MOOCs",

abstract = "There are a number of similarities and differences between FutureLearn MOOCs and those offered by other platforms, such as edX. In this research we compare the results of applying machine learning algorithms to predict course attrition for two case studies using datasets from a selected FutureLearn MOOC and an edX MOOC of comparable structure and themes. For each we have computed a number of attributes in a pre-processing stage from the raw data available in each course. Following this, we applied several machine learning algorithms on the pre-processed data to predict attrition levels for each course. The analysis suggests that the attribute selection varies in each scenario, which also impacts on the behaviour of the predicting algorithms.",

keywords = "MOOCs, Predictive model, Learning analytics, Attribute selection, FutureLearn, edX",

author = "Ruth Cobos and Adriana Wilde and Ed Zaluska",

note = "This work has been funded by the Web Science Institute Pump-priming 2015/16 Project “The MOOC Observatory Dashboard: Management, analysis and visualisation of MOOC data ”. Additionally, Ruth Cobos{\textquoteright} contribution has been partially funded by the Madrid Regional Government with grant No. S2013/ICE - 2715, the Spanish Ministry of Economy and Competitiveness project {"}Flexor{"} (TIN2014- 52129- R).; FutureLearn Workshop in Learning Analytics and Knowledge 2017 (LAK17), LAK17 ; Conference date: 13-03-2017 Through 17-03-2017",

year = "2017",

month = mar,

day = "13",

language = "English",

url = "https://sites.google.com/site/lak17flworkshop/",

}

TY - CONF

T1 - Comparing attrition prediction in FutureLearn and edX MOOCs

AU - Cobos, Ruth

AU - Wilde, Adriana

AU - Zaluska, Ed

N1 - Conference code: 7

PY - 2017/3/13

Y1 - 2017/3/13

N2 - There are a number of similarities and differences between FutureLearn MOOCs and those offered by other platforms, such as edX. In this research we compare the results of applying machine learning algorithms to predict course attrition for two case studies using datasets from a selected FutureLearn MOOC and an edX MOOC of comparable structure and themes. For each we have computed a number of attributes in a pre-processing stage from the raw data available in each course. Following this, we applied several machine learning algorithms on the pre-processed data to predict attrition levels for each course. The analysis suggests that the attribute selection varies in each scenario, which also impacts on the behaviour of the predicting algorithms.

AB - There are a number of similarities and differences between FutureLearn MOOCs and those offered by other platforms, such as edX. In this research we compare the results of applying machine learning algorithms to predict course attrition for two case studies using datasets from a selected FutureLearn MOOC and an edX MOOC of comparable structure and themes. For each we have computed a number of attributes in a pre-processing stage from the raw data available in each course. Following this, we applied several machine learning algorithms on the pre-processed data to predict attrition levels for each course. The analysis suggests that the attribute selection varies in each scenario, which also impacts on the behaviour of the predicting algorithms.

KW - MOOCs

KW - Predictive model

KW - Learning analytics

KW - Attribute selection

KW - FutureLearn

KW - edX

M3 - Paper

T2 - FutureLearn Workshop in Learning Analytics and Knowledge 2017 (LAK17)

Y2 - 13 March 2017 through 17 March 2017

ER -

Comparing attrition prediction in FutureLearn and edX MOOCs

Abstract

Workshop

Keywords

Access to Document

Fingerprint

Cite this