Sit Down Now: Computationally IdentifyingClassroom Management Practices

<a href="https://embed.stanford.edu/iframe/?url=https%3A%2F%2Fpurl.stanford.edu%2Fwv511dd3532" class="su-underline">Show Content</a>

Abstract/Contents

Abstract: Classroom management has been defined broadly as actions taken by a teacher to create and maintain an environment conducive to successful instruction. Competencies in behavior and classroom management practice significantly influence teacher retention, and academic and behavioral outcomes for students. Yet, identifying and improving classroom management practices at scale is challenging as existing methods require expensive annotation by experts. We propose the task of computationally classifying management practices in classroom discourse. We release an annotated dataset of teacher utterances and introduce two supervised computational approaches to identifying classroom management strategies. We train a supervised BERT model fine-tuned on our dataset to perform binary classification of whether an utterance includes classroom management and a supervised RoBERTa model fine-tuned on our dataset to predict a score along a scale between punitive and restorative management attitudes. Our predicted measures of classroom management show significant correlation with instruction quality, student and observer perceptions of classroom climate, student achievement and demographic factors. The performance of these classifiers indicates the potential for future automated evaluation and analysis of classroom management practices.

Type of resource	text
Publication date	March 30, 2023

Author	Tan, Mei
Advisor	Demszky, Dorottya

Subject	Classroom management
Subject	Natural language processing
Subject	Education data science
Genre	Text
Genre	Capstone
Genre	Student project report

DOI	https://doi.org/10.25740/wv511dd3532
Location	https://purl.stanford.edu/wv511dd3532

Use and reproduction: User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
License: This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International license (CC BY-NC).

Preferred citation: Tan, M. (2023). Sit Down Now: Computationally IdentifyingClassroom Management Practices. Stanford Digital Repository. Available at https://purl.stanford.edu/wv511dd3532. https://doi.org/10.25740/wv511dd3532.

Education Data Science (EDS) Capstone Projects, Graduate School of Education

Loading usage metrics...