Affective learning: improving engagement and enhancing learning with affect-aware feedback

Beate Grawemeyer, Manolis Mavrikis, Wayne Holmes, Sergio Gutiérrez-Santos, Michael Wiedmann, Nikol Rummel

Research output: Contribution to journalArticle

11 Citations (Scopus)
1 Downloads (Pure)

Abstract

This paper describes the design and ecologically valid evaluation of a learner model that lies at the heart of an intelligent learning environment called iTalk2Learn. A core objective of the learner model is to adapt formative feedback based on students’ affective states. Types of adaptation include what type of formative feedback should be provided and how it should be presented. Two Bayesian networks trained with data gathered in a series of Wizard-of-Oz studies are used for the adaptation process. This paper reports results from a quasi-experimental evaluation, in authentic classroom settings, which compared a version of iTalk2Learn that adapted feedback based on students’ affective states as they were talking aloud with the system (the affect condition) with one that provided feedback based only on the students’ performance (the non-affect condition). Our results suggest that affect-aware support contributes to reducing boredom and off-task behavior, and may have an effect on learning. We discuss the internal and ecological validity of the study, in light of pedagogical considerations that informed the design of the two conditions. Overall, the results of the study have implications both for the design of educational technology and for classroom approaches to teaching, because they highlight the important role that affect-aware modelling plays in the adaptive delivery of formative feedback to support learning.

Original languageEnglish
Pages (from-to)119-158
Number of pages40
JournalUser Modeling and User-Adapted Interaction
Volume27
Issue number1
Early online date7 Feb 2017
DOIs
Publication statusPublished - 1 Mar 2017
Externally publishedYes

Fingerprint

Feedback
learning
Students
Educational technology
boredom
classroom
student
Bayesian networks
educational technology
evaluation
Teaching
learning environment
performance

Bibliographical note

The final publication is available at Springer via http://dx.doi.org/10.1007/s11257-017-9188-z

Copyright © and Moral Rights are retained by the author(s) and/ or other copyright
owners. A copy can be downloaded for personal non-commercial research or study,
without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders.

Keywords

  • Affective learning
  • Bayesian networks
  • Formative feedback
  • Learner modelling

ASJC Scopus subject areas

  • Education
  • Human-Computer Interaction
  • Computer Science Applications

Cite this

Affective learning : improving engagement and enhancing learning with affect-aware feedback. / Grawemeyer, Beate; Mavrikis, Manolis; Holmes, Wayne; Gutiérrez-Santos, Sergio; Wiedmann, Michael; Rummel, Nikol.

In: User Modeling and User-Adapted Interaction, Vol. 27, No. 1, 01.03.2017, p. 119-158.

Research output: Contribution to journalArticle

Grawemeyer, Beate ; Mavrikis, Manolis ; Holmes, Wayne ; Gutiérrez-Santos, Sergio ; Wiedmann, Michael ; Rummel, Nikol. / Affective learning : improving engagement and enhancing learning with affect-aware feedback. In: User Modeling and User-Adapted Interaction. 2017 ; Vol. 27, No. 1. pp. 119-158.
@article{24b330a7758744c4a7ae8415bc838527,
title = "Affective learning: improving engagement and enhancing learning with affect-aware feedback",
abstract = "This paper describes the design and ecologically valid evaluation of a learner model that lies at the heart of an intelligent learning environment called iTalk2Learn. A core objective of the learner model is to adapt formative feedback based on students’ affective states. Types of adaptation include what type of formative feedback should be provided and how it should be presented. Two Bayesian networks trained with data gathered in a series of Wizard-of-Oz studies are used for the adaptation process. This paper reports results from a quasi-experimental evaluation, in authentic classroom settings, which compared a version of iTalk2Learn that adapted feedback based on students’ affective states as they were talking aloud with the system (the affect condition) with one that provided feedback based only on the students’ performance (the non-affect condition). Our results suggest that affect-aware support contributes to reducing boredom and off-task behavior, and may have an effect on learning. We discuss the internal and ecological validity of the study, in light of pedagogical considerations that informed the design of the two conditions. Overall, the results of the study have implications both for the design of educational technology and for classroom approaches to teaching, because they highlight the important role that affect-aware modelling plays in the adaptive delivery of formative feedback to support learning.",
keywords = "Affective learning, Bayesian networks, Formative feedback, Learner modelling",
author = "Beate Grawemeyer and Manolis Mavrikis and Wayne Holmes and Sergio Guti{\'e}rrez-Santos and Michael Wiedmann and Nikol Rummel",
note = "The final publication is available at Springer via http://dx.doi.org/10.1007/s11257-017-9188-z Copyright {\circledC} and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders.",
year = "2017",
month = "3",
day = "1",
doi = "10.1007/s11257-017-9188-z",
language = "English",
volume = "27",
pages = "119--158",
journal = "User Modelling and User-Adapted Interaction",
issn = "0924-1868",
publisher = "Springer Verlag",
number = "1",

}

TY - JOUR

T1 - Affective learning

T2 - improving engagement and enhancing learning with affect-aware feedback

AU - Grawemeyer, Beate

AU - Mavrikis, Manolis

AU - Holmes, Wayne

AU - Gutiérrez-Santos, Sergio

AU - Wiedmann, Michael

AU - Rummel, Nikol

N1 - The final publication is available at Springer via http://dx.doi.org/10.1007/s11257-017-9188-z Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders.

PY - 2017/3/1

Y1 - 2017/3/1

N2 - This paper describes the design and ecologically valid evaluation of a learner model that lies at the heart of an intelligent learning environment called iTalk2Learn. A core objective of the learner model is to adapt formative feedback based on students’ affective states. Types of adaptation include what type of formative feedback should be provided and how it should be presented. Two Bayesian networks trained with data gathered in a series of Wizard-of-Oz studies are used for the adaptation process. This paper reports results from a quasi-experimental evaluation, in authentic classroom settings, which compared a version of iTalk2Learn that adapted feedback based on students’ affective states as they were talking aloud with the system (the affect condition) with one that provided feedback based only on the students’ performance (the non-affect condition). Our results suggest that affect-aware support contributes to reducing boredom and off-task behavior, and may have an effect on learning. We discuss the internal and ecological validity of the study, in light of pedagogical considerations that informed the design of the two conditions. Overall, the results of the study have implications both for the design of educational technology and for classroom approaches to teaching, because they highlight the important role that affect-aware modelling plays in the adaptive delivery of formative feedback to support learning.

AB - This paper describes the design and ecologically valid evaluation of a learner model that lies at the heart of an intelligent learning environment called iTalk2Learn. A core objective of the learner model is to adapt formative feedback based on students’ affective states. Types of adaptation include what type of formative feedback should be provided and how it should be presented. Two Bayesian networks trained with data gathered in a series of Wizard-of-Oz studies are used for the adaptation process. This paper reports results from a quasi-experimental evaluation, in authentic classroom settings, which compared a version of iTalk2Learn that adapted feedback based on students’ affective states as they were talking aloud with the system (the affect condition) with one that provided feedback based only on the students’ performance (the non-affect condition). Our results suggest that affect-aware support contributes to reducing boredom and off-task behavior, and may have an effect on learning. We discuss the internal and ecological validity of the study, in light of pedagogical considerations that informed the design of the two conditions. Overall, the results of the study have implications both for the design of educational technology and for classroom approaches to teaching, because they highlight the important role that affect-aware modelling plays in the adaptive delivery of formative feedback to support learning.

KW - Affective learning

KW - Bayesian networks

KW - Formative feedback

KW - Learner modelling

UR - http://www.scopus.com/inward/record.url?scp=85011649929&partnerID=8YFLogxK

U2 - 10.1007/s11257-017-9188-z

DO - 10.1007/s11257-017-9188-z

M3 - Article

VL - 27

SP - 119

EP - 158

JO - User Modelling and User-Adapted Interaction

JF - User Modelling and User-Adapted Interaction

SN - 0924-1868

IS - 1

ER -