Cargando…

Siamese Neural Networks for Class Activity Detection

Classroom activity detection (CAD) aims at accurately recognizing speaker roles (either teacher or student) in classrooms. A CAD solution helps teachers get instant feedback on their pedagogical instructions. However, CAD is very challenging because (1) classroom conversations contain many conversat...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Hang, Wang, Zhiwei, Tang, Jiliang, Ding, Wenbiao, Liu, Zitao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7334716/
http://dx.doi.org/10.1007/978-3-030-52240-7_30
_version_ 1783553987945955328
author Li, Hang
Wang, Zhiwei
Tang, Jiliang
Ding, Wenbiao
Liu, Zitao
author_facet Li, Hang
Wang, Zhiwei
Tang, Jiliang
Ding, Wenbiao
Liu, Zitao
author_sort Li, Hang
collection PubMed
description Classroom activity detection (CAD) aims at accurately recognizing speaker roles (either teacher or student) in classrooms. A CAD solution helps teachers get instant feedback on their pedagogical instructions. However, CAD is very challenging because (1) classroom conversations contain many conversational turn-taking overlaps between teachers and students; (2) the CAD model needs to be generalized well enough for different teachers and students; and (3) classroom recordings may be very noisy and low-quality. In this work, we address the above challenges by building a Siamese neural framework to automatically identify teacher and student utterances from classroom recordings. The proposed model is evaluated on real-world educational datasets. The results demonstrate that (1) our approach is superior on the prediction tasks for both online and offline classroom environments; and (2) our framework exhibits robustness and generalization ability on new teachers (i.e., teachers never appear in training data).
format Online
Article
Text
id pubmed-7334716
institution National Center for Biotechnology Information
language English
publishDate 2020
record_format MEDLINE/PubMed
spelling pubmed-73347162020-07-06 Siamese Neural Networks for Class Activity Detection Li, Hang Wang, Zhiwei Tang, Jiliang Ding, Wenbiao Liu, Zitao Artificial Intelligence in Education Article Classroom activity detection (CAD) aims at accurately recognizing speaker roles (either teacher or student) in classrooms. A CAD solution helps teachers get instant feedback on their pedagogical instructions. However, CAD is very challenging because (1) classroom conversations contain many conversational turn-taking overlaps between teachers and students; (2) the CAD model needs to be generalized well enough for different teachers and students; and (3) classroom recordings may be very noisy and low-quality. In this work, we address the above challenges by building a Siamese neural framework to automatically identify teacher and student utterances from classroom recordings. The proposed model is evaluated on real-world educational datasets. The results demonstrate that (1) our approach is superior on the prediction tasks for both online and offline classroom environments; and (2) our framework exhibits robustness and generalization ability on new teachers (i.e., teachers never appear in training data). 2020-06-10 /pmc/articles/PMC7334716/ http://dx.doi.org/10.1007/978-3-030-52240-7_30 Text en © Springer Nature Switzerland AG 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Article
Li, Hang
Wang, Zhiwei
Tang, Jiliang
Ding, Wenbiao
Liu, Zitao
Siamese Neural Networks for Class Activity Detection
title Siamese Neural Networks for Class Activity Detection
title_full Siamese Neural Networks for Class Activity Detection
title_fullStr Siamese Neural Networks for Class Activity Detection
title_full_unstemmed Siamese Neural Networks for Class Activity Detection
title_short Siamese Neural Networks for Class Activity Detection
title_sort siamese neural networks for class activity detection
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7334716/
http://dx.doi.org/10.1007/978-3-030-52240-7_30
work_keys_str_mv AT lihang siameseneuralnetworksforclassactivitydetection
AT wangzhiwei siameseneuralnetworksforclassactivitydetection
AT tangjiliang siameseneuralnetworksforclassactivitydetection
AT dingwenbiao siameseneuralnetworksforclassactivitydetection
AT liuzitao siameseneuralnetworksforclassactivitydetection