skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


This content will become publicly available on July 15, 2026

Title: Investigating racial and skin tone biases in automated classification of teachers’ activities in classroom videos.
Previous studies have shown that artificial intelligence can be used to classify instruction-related activities in classroom videos. The automated classi- fication of human activities, however, is vulnerable to biases in which the model performs substantially better or worse for different people groups. Although algo- rithmic bias has been highlighted as an important area for research in artificial intelligence in education, there have been few studies that empirically investigate potential bias in instruction-related activity recognition systems. In this paper, we report on an investigation of potential racial and skin tone biases in the automated classification of teachers’ activities in classroom videos. We examine whether a neural network’s classification of teachers’ activities differs with respect to teacher race and skin tone and whether differently balanced training datasets affect the performance of the neural network. Our results indicate that, under ordinary class- room lighting conditions, the neural network performs equally well regardless of teacher race or skin tone. Furthermore, our results suggest the balance of the training dataset with respect to teacher skin tone and race has a small—but not necessarily positive—effect on the neural network’s performance. Our study, how- ever, also suggests the importance of quality lighting for accurate classification of teacher-related instructional activities for teachers of color. We conclude with a discussion of our mixed findings, the limitations of our study, and potential directions for future research.  more » « less
Award ID(s):
2000487
PAR ID:
10653835
Author(s) / Creator(s):
; ;
Corporate Creator(s):
Publisher / Repository:
Springer Nature Switzerland
Date Published:
Edition / Version:
1
Volume:
1
Issue:
1
ISBN:
978-3-031-98419-8
Subject(s) / Keyword(s):
Bias Classroom activity recognition Computer vision
Format(s):
Medium: X Size: 476KB Other: pdfa
Size(s):
476KB
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, Journal of Learning Analytics)
    Khosravi, H (Ed.)
    Despite a tremendous increase in the use of video for conducting research in classrooms as well as preparing and evaluating teachers, there remain notable challenges to using classroom videos at scale, including time and financial costs. Recent advances in artificial intelligence could make the process of analyzing, scoring, and cataloguing videos more efficient. These advances include natural language processing, automated speech recognition, and deep neural networks. To train artificial intelligence to accurately classify activities in classroom videos, humans must first annotate a set of videos in a consistent way. This paper describes our investigation of the degree of inter-annotator reliability regarding identification of and duration of activities among annotators with and without experience analyzing classroom videos. Validity of human annotations is crucial for research involving temporal analysis within classroom video research. The study reported here represents an important step towards applying methods developed in other fields to validate temporal analytics within learning analytics research for classifying time- and event-based activities in classroom videos. 
    more » « less
  2. ; (, North_American_Chapter_of_the_International_Group_for_the_Psychology_of_Mathematics_Education)
    Artificial intelligence (AI) can be used to classify instruction-related activities from classroom videos. These AI models, however, are dependent on datasets that are used to train the model to recognize patterns and make predictions. Imbalances in datasets used for training—such as imbalances in the domain of mathematics featured in videos of classroom instruction—may bias a model’s performance, sometimes in unforeseen ways. In this study, we investigate whether an imbalanced training dataset with a disproportionate number of video recordings of lessons focused on Number and Operations and Algebra in elementary mathematics classrooms yielded differences in a model’s performance in other mathematical content domains. We analyze an AI model’s classification of 24 instructional activities and found a notable and unanticipated difference in the model’s performance for one of the mathematical content domains. 
    more » « less
  3. ; (, EXCELLENCE AND INNOVATION IN LEARNING AND TEACHING)
    Simulated teaching environments have been used for more than two decades and are likely to continue to expand to meet the demands of teacher development programs. In this study, the self-reported changes in culturally-responsive teaching perceptions of ten classroom teachers serving more than six hundred students are reported. This paper includes first year findings from a program designed to use artificial-intelligence (AI) based algorithms to reduce implicit bias in teaching. Findings from this study include significant pre-post increases for self-efficacy related to culturally responsive teaching as well as instructional self-efficacy. These findings add credibility to the contention that a key innovation of using simulation programs for teacher professional development is that it provides teachers and teacher trainees many learning trials with simulated students, thereby increasing teacher confidence and competence, and which in turn will improve student learning. Findings set the stage for measuring the impact on student perceptions of learning and cultural engagement intended to support teachers in recognizing and ameliorating their own implicit biases. 
    more » « less
  4. ; ; ; ; ; ; ; ; ; (, Journal of Special Education Preparation)
    The options for Artificial intelligence (AI) tools used in teacher education are increasing daily, but more is only sometimes better for teachers working in already complex classroom settings. This team discusses the increase of AI in schools and provides an example from administrators, teacher educators, and computer scientists of an AI virtual agent and the research to support student learning and teachers in classroom settings. The authors discuss the creation and potential of virtual characters in elementary classrooms, combined with biometrics and facial emotional recognition, which in this study has impacted student learning and offered support to the teacher. The researchers share the development of the AI agent, the lessons learned, the integration of biometrics and facial tracking, and how teachers use this emerging form of AI both in classroom-based center activities and to support students’ emotional regulation. The authors conclude by describing the application of this type of support in teacher preparation programs and a vision of the future of using AI agents in instruction. 
    more » « less
  5. ; (, The Spanish Journal of Psychology)
    Abstract School represents an important context for children’s social, moral, and identity development. Research indicates that supportive teacher-student relationships are significantly related to positive student academic achievement. Unfortunately, teacher bias as well as peer exclusion based on group identity (gender, race, ethnicity, and nationality) pervade many school contexts. The presence of these biases in the classroom is negatively related to students’ academic development, especially for children who are minoritized and marginalized. Very little research has connected teacher bias and children’s reasoning about bias and inequalities in the classroom context. The classroom is a complex environment in which to examine children’s social and moral reasoning about bias, given teachers’ position of authority which often includes power, status, and prestige. We propose that understanding both teacher bias and peer intergroup exclusion are essential for promoting more fair classrooms. This paper reviews foundational theory as well as the social reasoning developmental model as a framework for studying how children think about fairness and bias in the classroom context. We then discuss current research on children’s social-cognitive and moral capacities, particularly in the contexts of societal inequality and social inclusion or exclusion. Finally, this article proposes new directions for research to promote fairness and inclusivity in schools and suggests how these new lines of research might inform school-based interventions. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email