An Application of Extreme Value Theory to Learning Analytics: Predicting Collaboration Outcome from Eye-Tracking Data

22 Pages Posted: 30 Aug 2016 Last revised: 13 Mar 2017

See all articles by Kshitij Sharma

Kshitij Sharma

University of Lausanne - School of Economics and Business Administration (HEC-Lausanne); Ecole Polytechnique Fédérale de Lausanne

Valérie Chavez-Demoulin

University of Lausanne - School of Economics and Business Administration (HEC-Lausanne)

Pierre Dillenbourg

Ecole Polytechnique Fédérale de Lausanne

Date Written: August 19, 2016

Abstract

The statistics used in education research are based on central trends such as the mean or standard deviation, discarding outliers. This paper adopts another viewpoint that has emerged in Statistics, called the Extreme Value Theory (EVT). EVT claims that the bulk of the normal distribution is mostly comprised of uninteresting variations while the most extreme values convey more information. We applied EVT to eye-tracking data collected during online collaborative problem solving with the aim of predicting the quality of collaboration. We compare our previous approach, based on central trends, with an EVT approach focused on extreme episodes of collaboration. The latter occurred to provide a better prediction of the quality of collaboration.

Keywords: Eye-tracking, Dual eye-tracking, Extreme value theory, Computer Supported Collaborative learning, Learning Analytics, Collaboration quality

Suggested Citation

Sharma, Kshitij and Chavez-Demoulin, Valérie and Dillenbourg, Pierre, An Application of Extreme Value Theory to Learning Analytics: Predicting Collaboration Outcome from Eye-Tracking Data (August 19, 2016). Available at SSRN: https://ssrn.com/abstract=2831445 or http://dx.doi.org/10.2139/ssrn.2831445

Kshitij Sharma (Contact Author)

University of Lausanne - School of Economics and Business Administration (HEC-Lausanne) ( email )

Unil Dorigny, Batiment Internef
Lausanne, 1015
Switzerland

Ecole Polytechnique Fédérale de Lausanne

RLC D1 740
Station 20
Lausanne, Vaud 1015
Switzerland

Valérie Chavez-Demoulin

University of Lausanne - School of Economics and Business Administration (HEC-Lausanne) ( email )

Unil Dorigny, Batiment Anthropole
Lausanne, 1015
Switzerland

HOME PAGE: http://https://www.hec.unil.ch/people/vchavez&vue=contact&set_language=en&cl=en

Pierre Dillenbourg

Ecole Polytechnique Fédérale de Lausanne

RLC D1 740
Station 20
1015 Lausanne, Vaud 1015
Switzerland

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
93
Abstract Views
1,065
rank
354,860
PlumX Metrics