Inferring the climate in classrooms from audio and video recordings: a machine learning approach

Anusha James; Mohan Kashyap; Yi Han Victoria Chua; Tomasz Maszczyk; Ana Moreno Nunez; Rebecca Bull; Justin Dauwels

doi:10.1109/TALE.2018.8615327

Inferring the climate in classrooms from audio and video recordings: a machine learning approach

Anusha James, Mohan Kashyap, Yi Han Victoria Chua, Tomasz Maszczyk, Ana Moreno Nunez, Rebecca Bull, Justin Dauwels

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

9 Citations (Scopus)

Abstract

The classroom climate is shaped by a combination of teacher practices and peer relationships. The Classroom Assessment Scoring System (CLASS) has been designed to observe and code classroom interactions between students and teachers in order to provide formative feedback on teaching practices and improve teacher instruction. But the turnover time for training, observing and coding makes it hard to generate instant feedback. Since there are few automated assessment tools designed to measure the classroom climate, we propose a novel system for automatic assessment of classroom climate, based on speech, behavioral cues and video features by applying machine learning techniques. This paper elaborates on the design and validation of an audio-video analytics platform for predicting classroom climate. Employing machine learning classifiers instead of subjective measures can ease and expedite the coding. We presume our system can empower education systems to continuously review and improve teaching strategies thus promoting smart classroom in the future.

Original language	English
Title of host publication	TALE 2018
Subtitle of host publication	Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering
Editors	Mark J.W. Lee, Sasha Nikolic, Montserrat Ros, Jun Shen, Leon C. U. Lei, Gary K.W. Wong, Neelakantam Venkatarayalu
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	983-988
Number of pages	6
ISBN (Electronic)	9781538665220
DOIs	https://doi.org/10.1109/TALE.2018.8615327
Publication status	Published - 16 Jan 2019
Externally published	Yes
Event	2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018 - Wollongong, Australia Duration: 4 Dec 2018 → 7 Dec 2018

Publication series

Name	IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE)
ISSN (Electronic)	2470-6698

Conference

Conference	2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018
Country/Territory	Australia
City	Wollongong
Period	4/12/18 → 7/12/18

Keywords

classroom climate prediction
machine learning
audio-video analytics
social behavior
educational research

Access to Document

10.1109/TALE.2018.8615327

Cite this

James, A., Kashyap, M., Chua, Y. H. V., Maszczyk, T., Nunez, A. M., Bull, R., & Dauwels, J. (2019). Inferring the climate in classrooms from audio and video recordings: a machine learning approach. In M. J. W. Lee, S. Nikolic, M. Ros, J. Shen, L. C. U. Lei, G. K. W. Wong, & N. Venkatarayalu (Eds.), TALE 2018: Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (pp. 983-988). [8615327] (IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE)). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/TALE.2018.8615327

James, Anusha ; Kashyap, Mohan ; Chua, Yi Han Victoria ; Maszczyk, Tomasz ; Nunez, Ana Moreno ; Bull, Rebecca ; Dauwels, Justin. / Inferring the climate in classrooms from audio and video recordings : a machine learning approach. TALE 2018: Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering. editor / Mark J.W. Lee ; Sasha Nikolic ; Montserrat Ros ; Jun Shen ; Leon C. U. Lei ; Gary K.W. Wong ; Neelakantam Venkatarayalu. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2019. pp. 983-988 (IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE)).

@inproceedings{1f9ccc7539b94f16b50803ea8a2d0fe1,

title = "Inferring the climate in classrooms from audio and video recordings: a machine learning approach",

abstract = "The classroom climate is shaped by a combination of teacher practices and peer relationships. The Classroom Assessment Scoring System (CLASS) has been designed to observe and code classroom interactions between students and teachers in order to provide formative feedback on teaching practices and improve teacher instruction. But the turnover time for training, observing and coding makes it hard to generate instant feedback. Since there are few automated assessment tools designed to measure the classroom climate, we propose a novel system for automatic assessment of classroom climate, based on speech, behavioral cues and video features by applying machine learning techniques. This paper elaborates on the design and validation of an audio-video analytics platform for predicting classroom climate. Employing machine learning classifiers instead of subjective measures can ease and expedite the coding. We presume our system can empower education systems to continuously review and improve teaching strategies thus promoting smart classroom in the future.",

keywords = "classroom climate prediction, machine learning, audio-video analytics, social behavior, educational research",

author = "Anusha James and Mohan Kashyap and Chua, {Yi Han Victoria} and Tomasz Maszczyk and Nunez, {Ana Moreno} and Rebecca Bull and Justin Dauwels",

year = "2019",

month = jan,

day = "16",

doi = "10.1109/TALE.2018.8615327",

language = "English",

series = "IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "983--988",

editor = "Lee, {Mark J.W.} and Sasha Nikolic and Montserrat Ros and Jun Shen and Lei, {Leon C. U.} and Wong, {Gary K.W.} and Neelakantam Venkatarayalu",

booktitle = "TALE 2018",

address = "United States",

note = "2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018 ; Conference date: 04-12-2018 Through 07-12-2018",

}

James, A, Kashyap, M, Chua, YHV, Maszczyk, T, Nunez, AM, Bull, R & Dauwels, J 2019, Inferring the climate in classrooms from audio and video recordings: a machine learning approach. in MJW Lee, S Nikolic, M Ros, J Shen, LCU Lei, GKW Wong & N Venkatarayalu (eds), TALE 2018: Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering., 8615327, IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE), Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 983-988, 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018, Wollongong, Australia, 4/12/18. https://doi.org/10.1109/TALE.2018.8615327

Inferring the climate in classrooms from audio and video recordings : a machine learning approach. / James, Anusha; Kashyap, Mohan; Chua, Yi Han Victoria; Maszczyk, Tomasz; Nunez, Ana Moreno; Bull, Rebecca; Dauwels, Justin.

TALE 2018: Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering. ed. / Mark J.W. Lee; Sasha Nikolic; Montserrat Ros; Jun Shen; Leon C. U. Lei; Gary K.W. Wong; Neelakantam Venkatarayalu. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2019. p. 983-988 8615327 (IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE)).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Inferring the climate in classrooms from audio and video recordings

T2 - 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018

AU - James, Anusha

AU - Kashyap, Mohan

AU - Chua, Yi Han Victoria

AU - Maszczyk, Tomasz

AU - Nunez, Ana Moreno

AU - Bull, Rebecca

AU - Dauwels, Justin

PY - 2019/1/16

Y1 - 2019/1/16

N2 - The classroom climate is shaped by a combination of teacher practices and peer relationships. The Classroom Assessment Scoring System (CLASS) has been designed to observe and code classroom interactions between students and teachers in order to provide formative feedback on teaching practices and improve teacher instruction. But the turnover time for training, observing and coding makes it hard to generate instant feedback. Since there are few automated assessment tools designed to measure the classroom climate, we propose a novel system for automatic assessment of classroom climate, based on speech, behavioral cues and video features by applying machine learning techniques. This paper elaborates on the design and validation of an audio-video analytics platform for predicting classroom climate. Employing machine learning classifiers instead of subjective measures can ease and expedite the coding. We presume our system can empower education systems to continuously review and improve teaching strategies thus promoting smart classroom in the future.

AB - The classroom climate is shaped by a combination of teacher practices and peer relationships. The Classroom Assessment Scoring System (CLASS) has been designed to observe and code classroom interactions between students and teachers in order to provide formative feedback on teaching practices and improve teacher instruction. But the turnover time for training, observing and coding makes it hard to generate instant feedback. Since there are few automated assessment tools designed to measure the classroom climate, we propose a novel system for automatic assessment of classroom climate, based on speech, behavioral cues and video features by applying machine learning techniques. This paper elaborates on the design and validation of an audio-video analytics platform for predicting classroom climate. Employing machine learning classifiers instead of subjective measures can ease and expedite the coding. We presume our system can empower education systems to continuously review and improve teaching strategies thus promoting smart classroom in the future.

KW - classroom climate prediction

KW - machine learning

KW - audio-video analytics

KW - social behavior

KW - educational research

UR - http://www.scopus.com/inward/record.url?scp=85062097352&partnerID=8YFLogxK

U2 - 10.1109/TALE.2018.8615327

DO - 10.1109/TALE.2018.8615327

M3 - Conference proceeding contribution

AN - SCOPUS:85062097352

T3 - IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE)

SP - 983

EP - 988

BT - TALE 2018

A2 - Lee, Mark J.W.

A2 - Nikolic, Sasha

A2 - Ros, Montserrat

A2 - Shen, Jun

A2 - Lei, Leon C. U.

A2 - Wong, Gary K.W.

A2 - Venkatarayalu, Neelakantam

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

Y2 - 4 December 2018 through 7 December 2018

ER -

James A, Kashyap M, Chua YHV, Maszczyk T, Nunez AM, Bull R et al. Inferring the climate in classrooms from audio and video recordings: a machine learning approach. In Lee MJW, Nikolic S, Ros M, Shen J, Lei LCU, Wong GKW, Venkatarayalu N, editors, TALE 2018: Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). 2019. p. 983-988. 8615327. (IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE)). https://doi.org/10.1109/TALE.2018.8615327

Inferring the climate in classrooms from audio and video recordings: a machine learning approach

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

SKIP: Singapore Kindergarten Impact Project

Cite this

Inferring the climate in classrooms from audio and video recordings: a machine learning approach

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

SKIP: Singapore Kindergarten Impact Project

Cite this