Automatic Assessment of Students' Classroom Engagement with Bias Mitigated Multi-task Model

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Thiering, James, Krishna, Tarun Sethupat Radha, Zelkin, Dylan, Biswas, Ashis Kumer
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918171157463040
author Thiering, James
Krishna, Tarun Sethupat Radha
Zelkin, Dylan
Biswas, Ashis Kumer
author_facet Thiering, James
Krishna, Tarun Sethupat Radha
Zelkin, Dylan
Biswas, Ashis Kumer
contents With the rise of online and virtual learning, monitoring and enhancing student engagement have become an important aspect of effective education. Traditional methods of assessing a student's involvement might not be applicable directly to virtual environments. In this study, we focused on this problem and addressed the need to develop an automated system to detect student engagement levels during online learning. We proposed a novel training method which can discourage a model from leveraging sensitive features like gender for its predictions. The proposed method offers benefits not only in the enforcement of ethical standards, but also to enhance interpretability of the model predictions. We applied an attribute-orthogonal regularization technique to a split-model classifier, which uses multiple transfer learning strategies to achieve effective results in reducing disparity in the distribution of prediction for sensitivity groups from a Pearson correlation coefficient of 0.897 for the unmitigated model, to 0.999 for the mitigated model. The source code for this project is available on https://github.com/ashiskb/elearning-engagement-study .
format Preprint
id arxiv_https___arxiv_org_abs_2510_22057
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automatic Assessment of Students' Classroom Engagement with Bias Mitigated Multi-task Model
Thiering, James
Krishna, Tarun Sethupat Radha
Zelkin, Dylan
Biswas, Ashis Kumer
Machine Learning
Artificial Intelligence
Computers and Society
I.5.1; I.4.7
With the rise of online and virtual learning, monitoring and enhancing student engagement have become an important aspect of effective education. Traditional methods of assessing a student's involvement might not be applicable directly to virtual environments. In this study, we focused on this problem and addressed the need to develop an automated system to detect student engagement levels during online learning. We proposed a novel training method which can discourage a model from leveraging sensitive features like gender for its predictions. The proposed method offers benefits not only in the enforcement of ethical standards, but also to enhance interpretability of the model predictions. We applied an attribute-orthogonal regularization technique to a split-model classifier, which uses multiple transfer learning strategies to achieve effective results in reducing disparity in the distribution of prediction for sensitivity groups from a Pearson correlation coefficient of 0.897 for the unmitigated model, to 0.999 for the mitigated model. The source code for this project is available on https://github.com/ashiskb/elearning-engagement-study .
title Automatic Assessment of Students' Classroom Engagement with Bias Mitigated Multi-task Model
topic Machine Learning
Artificial Intelligence
Computers and Society
I.5.1; I.4.7
url https://arxiv.org/abs/2510.22057