Detecting Teacher Expertise in an Immersive VR Classroom : Leveraging Fused Sensor Data with Explainable Machine Learning Models
(2023) 22nd IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2023 In Proceedings - 2023 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2023 p.683-692- Abstract
Currently, VR technology is increasingly being used in applications to enable immersive yet controlled research settings. One such area of research is expertise assessment, where novel technological approaches to collecting process data, specifically eye tracking, in combination with explainable models, can provide insights into assessing and training novices, as well as fostering expertise development. We present a machine learning approach to predict teacher expertise by leveraging data from an off-the-shelf VR device collected in a VirATec study. By fusing eye-tracking and controller-tracking data, teachers' recognition and handling of disruptive events in the classroom are taken into account or considered. Three classification... (More)
Currently, VR technology is increasingly being used in applications to enable immersive yet controlled research settings. One such area of research is expertise assessment, where novel technological approaches to collecting process data, specifically eye tracking, in combination with explainable models, can provide insights into assessing and training novices, as well as fostering expertise development. We present a machine learning approach to predict teacher expertise by leveraging data from an off-the-shelf VR device collected in a VirATec study. By fusing eye-tracking and controller-tracking data, teachers' recognition and handling of disruptive events in the classroom are taken into account or considered. Three classification models were compared, including SVM, Random Forest, and LightGBM, with Random Forest achieving the best ROC-AUC score of 0.768 in predicting teacher expertise. The SHAP approach to model interpretation revealed informative features (e.g., fixations on identified disruptive students) for distinguishing teacher expertise. Our study serves as a pioneering effort in assessing teacher expertise using eye tracking within an interactive virtual setting, paving the way for future research and advancements in the field.
(Less)
- author
- Gao, Hong LU ; Bozkir, Efe ; Stark, Philipp LU ; Goldberg, Patricia ; Meixner, Gerrit ; Kasneci, Enkelejda and Gollner, Richard
- publishing date
- 2023
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Classification and regression trees, Computing methodologies, Human computer interaction (HCI), Human-centered computing, Interaction paradigms, Machine learning, Machine learning approaches, Virtual reality
- host publication
- Proceedings - 2023 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2023
- series title
- Proceedings - 2023 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2023
- editor
- Bruder, Gerd ; Olivier, Anne-Helene ; Cunningham, Andrew ; Peng, Evan Yifan ; Grubert, Jens and Williams, Ian
- pages
- 10 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 22nd IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2023
- conference location
- Sydney, Australia
- conference dates
- 2023-10-16 - 2023-10-20
- external identifiers
-
- scopus:85180368706
- ISBN
- 9798350328387
- DOI
- 10.1109/ISMAR59233.2023.00083
- language
- English
- LU publication?
- no
- additional info
- Publisher Copyright: © 2023 IEEE.
- id
- 81892beb-9760-4554-86ec-fed336d43037
- date added to LUP
- 2024-10-15 08:49:40
- date last changed
- 2025-04-04 15:26:00
@inproceedings{81892beb-9760-4554-86ec-fed336d43037,
abstract = {{<p>Currently, VR technology is increasingly being used in applications to enable immersive yet controlled research settings. One such area of research is expertise assessment, where novel technological approaches to collecting process data, specifically eye tracking, in combination with explainable models, can provide insights into assessing and training novices, as well as fostering expertise development. We present a machine learning approach to predict teacher expertise by leveraging data from an off-the-shelf VR device collected in a VirATec study. By fusing eye-tracking and controller-tracking data, teachers' recognition and handling of disruptive events in the classroom are taken into account or considered. Three classification models were compared, including SVM, Random Forest, and LightGBM, with Random Forest achieving the best ROC-AUC score of 0.768 in predicting teacher expertise. The SHAP approach to model interpretation revealed informative features (e.g., fixations on identified disruptive students) for distinguishing teacher expertise. Our study serves as a pioneering effort in assessing teacher expertise using eye tracking within an interactive virtual setting, paving the way for future research and advancements in the field.</p>}},
author = {{Gao, Hong and Bozkir, Efe and Stark, Philipp and Goldberg, Patricia and Meixner, Gerrit and Kasneci, Enkelejda and Gollner, Richard}},
booktitle = {{Proceedings - 2023 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2023}},
editor = {{Bruder, Gerd and Olivier, Anne-Helene and Cunningham, Andrew and Peng, Evan Yifan and Grubert, Jens and Williams, Ian}},
isbn = {{9798350328387}},
keywords = {{Classification and regression trees; Computing methodologies; Human computer interaction (HCI); Human-centered computing; Interaction paradigms; Machine learning; Machine learning approaches; Virtual reality}},
language = {{eng}},
pages = {{683--692}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{Proceedings - 2023 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2023}},
title = {{Detecting Teacher Expertise in an Immersive VR Classroom : Leveraging Fused Sensor Data with Explainable Machine Learning Models}},
url = {{http://dx.doi.org/10.1109/ISMAR59233.2023.00083}},
doi = {{10.1109/ISMAR59233.2023.00083}},
year = {{2023}},
}