Learning Analytics Should Analyse the Learning: Proposing a Generic Stealth Assessment Tool

Konstantinos Georgiadis, Giel van Lankveld, Kiavash Bahreini, Wim Westera

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

Stealth assessment could radically extend the scope and impact of learning analytics. Stealth assessment refers to the unobtrusive assessment of learners by exploiting emerging data from their digital traces in electronic learning environments through machine learning technologies. So far, stealth assessment has been studied extensively in serious games, but has not been widely applied, as it is a laborious and complex methodology for which no support tools are available. This study proposes a generic tool for the arrangement of stealth assessment to remove its current limitations and pave the road for its wider adoption. It describes the conceptual design of such a tool including its requirements regarding users, functions, and workflow. A prototype was implemented as a basic console application covering the tool's core requirements, including a Gaussian Naïve Bayes Network utility. Generated input files were used fortesting and validating the approach. In a controlled test condition the stealth assessment classification accuracy was found to be inherently stable and high (typically above 92%). It is argued that the proposed approach could radically increase the applicability of stealth assessment in serious games and inform current learning analytics approaches with unobtrusive, more detailed and genuine assessments of learning.
Original languageEnglish
Title of host publicationIEEE Conference on Games 2019
Subtitle of host publicationLondon, United Kingdom 20-23 August 2019
PublisherIEEE
Pages1017-1024
Number of pages8
ISBN (Electronic)9781728118840
ISBN (Print)9781728118857
DOIs
Publication statusPublished - 26 Sep 2019
EventIEEE Conference on Games (CoG) 2019 - Queen Mary University of London, London, United Kingdom
Duration: 20 Aug 201923 Aug 2019
http://ieee-cog.org/2019/

Conference

ConferenceIEEE Conference on Games (CoG) 2019
Abbreviated titleCOG 2019
CountryUnited Kingdom
CityLondon
Period20/08/1923/08/19
Internet address

Fingerprint

Conceptual design
Learning systems
Serious games

Cite this

Georgiadis, K., van Lankveld, G., Bahreini, K., & Westera, W. (2019). Learning Analytics Should Analyse the Learning: Proposing a Generic Stealth Assessment Tool. In IEEE Conference on Games 2019: London, United Kingdom 20-23 August 2019 (pp. 1017-1024). IEEE. https://doi.org/10.1109/CIG.2019.8847960
Georgiadis, Konstantinos ; van Lankveld, Giel ; Bahreini, Kiavash ; Westera, Wim. / Learning Analytics Should Analyse the Learning : Proposing a Generic Stealth Assessment Tool. IEEE Conference on Games 2019: London, United Kingdom 20-23 August 2019. IEEE, 2019. pp. 1017-1024
@inproceedings{e300e6cd52c94b869302899457bd21a5,
title = "Learning Analytics Should Analyse the Learning: Proposing a Generic Stealth Assessment Tool",
abstract = "Stealth assessment could radically extend the scope and impact of learning analytics. Stealth assessment refers to the unobtrusive assessment of learners by exploiting emerging data from their digital traces in electronic learning environments through machine learning technologies. So far, stealth assessment has been studied extensively in serious games, but has not been widely applied, as it is a laborious and complex methodology for which no support tools are available. This study proposes a generic tool for the arrangement of stealth assessment to remove its current limitations and pave the road for its wider adoption. It describes the conceptual design of such a tool including its requirements regarding users, functions, and workflow. A prototype was implemented as a basic console application covering the tool's core requirements, including a Gaussian Na{\"i}ve Bayes Network utility. Generated input files were used fortesting and validating the approach. In a controlled test condition the stealth assessment classification accuracy was found to be inherently stable and high (typically above 92{\%}). It is argued that the proposed approach could radically increase the applicability of stealth assessment in serious games and inform current learning analytics approaches with unobtrusive, more detailed and genuine assessments of learning.",
author = "Konstantinos Georgiadis and {van Lankveld}, Giel and Kiavash Bahreini and Wim Westera",
year = "2019",
month = "9",
day = "26",
doi = "10.1109/CIG.2019.8847960",
language = "English",
isbn = "9781728118857",
pages = "1017--1024",
booktitle = "IEEE Conference on Games 2019",
publisher = "IEEE",
address = "United States",

}

Georgiadis, K, van Lankveld, G, Bahreini, K & Westera, W 2019, Learning Analytics Should Analyse the Learning: Proposing a Generic Stealth Assessment Tool. in IEEE Conference on Games 2019: London, United Kingdom 20-23 August 2019. IEEE, pp. 1017-1024, IEEE Conference on Games (CoG) 2019, London, United Kingdom, 20/08/19. https://doi.org/10.1109/CIG.2019.8847960

Learning Analytics Should Analyse the Learning : Proposing a Generic Stealth Assessment Tool. / Georgiadis, Konstantinos; van Lankveld, Giel; Bahreini, Kiavash; Westera, Wim.

IEEE Conference on Games 2019: London, United Kingdom 20-23 August 2019. IEEE, 2019. p. 1017-1024.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

TY - GEN

T1 - Learning Analytics Should Analyse the Learning

T2 - Proposing a Generic Stealth Assessment Tool

AU - Georgiadis, Konstantinos

AU - van Lankveld, Giel

AU - Bahreini, Kiavash

AU - Westera, Wim

PY - 2019/9/26

Y1 - 2019/9/26

N2 - Stealth assessment could radically extend the scope and impact of learning analytics. Stealth assessment refers to the unobtrusive assessment of learners by exploiting emerging data from their digital traces in electronic learning environments through machine learning technologies. So far, stealth assessment has been studied extensively in serious games, but has not been widely applied, as it is a laborious and complex methodology for which no support tools are available. This study proposes a generic tool for the arrangement of stealth assessment to remove its current limitations and pave the road for its wider adoption. It describes the conceptual design of such a tool including its requirements regarding users, functions, and workflow. A prototype was implemented as a basic console application covering the tool's core requirements, including a Gaussian Naïve Bayes Network utility. Generated input files were used fortesting and validating the approach. In a controlled test condition the stealth assessment classification accuracy was found to be inherently stable and high (typically above 92%). It is argued that the proposed approach could radically increase the applicability of stealth assessment in serious games and inform current learning analytics approaches with unobtrusive, more detailed and genuine assessments of learning.

AB - Stealth assessment could radically extend the scope and impact of learning analytics. Stealth assessment refers to the unobtrusive assessment of learners by exploiting emerging data from their digital traces in electronic learning environments through machine learning technologies. So far, stealth assessment has been studied extensively in serious games, but has not been widely applied, as it is a laborious and complex methodology for which no support tools are available. This study proposes a generic tool for the arrangement of stealth assessment to remove its current limitations and pave the road for its wider adoption. It describes the conceptual design of such a tool including its requirements regarding users, functions, and workflow. A prototype was implemented as a basic console application covering the tool's core requirements, including a Gaussian Naïve Bayes Network utility. Generated input files were used fortesting and validating the approach. In a controlled test condition the stealth assessment classification accuracy was found to be inherently stable and high (typically above 92%). It is argued that the proposed approach could radically increase the applicability of stealth assessment in serious games and inform current learning analytics approaches with unobtrusive, more detailed and genuine assessments of learning.

U2 - 10.1109/CIG.2019.8847960

DO - 10.1109/CIG.2019.8847960

M3 - Conference article in proceeding

SN - 9781728118857

SP - 1017

EP - 1024

BT - IEEE Conference on Games 2019

PB - IEEE

ER -

Georgiadis K, van Lankveld G, Bahreini K, Westera W. Learning Analytics Should Analyse the Learning: Proposing a Generic Stealth Assessment Tool. In IEEE Conference on Games 2019: London, United Kingdom 20-23 August 2019. IEEE. 2019. p. 1017-1024 https://doi.org/10.1109/CIG.2019.8847960