An official website of the United States government
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
This content will become publicly available on November 1, 2026
Addressing imbalance: Evaluating whether instructional activities classifications differ by mathematics content domains.
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
- Award ID(s):
- 2000487
- PAR ID:
- 10653837
- Publisher / Repository:
- North_American_Chapter_of_the_International_Group_for_the_Psychology_of_Mathematics_Education
- Date Published:
- Edition / Version:
- 1
- Volume:
- 1
- Issue:
- 1
- Page Range / eLocation ID:
- 1-9
- Subject(s) / Keyword(s):
- Elementary school education technology
- Format(s):
- Medium: X Size: 254KB Other: pdfa
- Size(s):
- 254KB
- Location:
- Pittsburgh, PA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Incorporating modeling activities into classroom instruction requires flexibility with pedagogical content knowledge and the ability to understand and interpret students’ thinking, skills that teachers often develop through experience. One way to support preservice mathematics teachers’ (PSMTs) proficiency with mathematical modeling is by incorporating modeling tasks into mathematics pedagogy courses, allowing PSMTs to engage with mathematical modeling as students and as future teachers. Eight PSMTs participated in a model-eliciting activity (MEA) in which they were asked to develop a model that describes the strength of the magnetic field generated by a solenoid. By engaging in mathematical modeling as students, these PSMTs became aware of their own proficiency with and understanding of mathematical modeling. By engaging inmathematical modeling as future teachers, these PSMTs were able to articulate the importance of incorporating MEAs into their own instruction.more » « less
-
Lischka, A. E. (Ed.)Engagement in the mathematics classroom through interactions with the instructor, peers, and content are necessary for an effective learning experience. As such, it is important to understand the types of interactions that teachers utilize to engage students, especially as they have had to shift from a complete face-to-face setting to various remote modalities. Utilizing four interaction types (learner-content, learner-instructor, learner-learner, and learner-interface) this paper analyzes 35 videos of classroom instruction with the purpose of describing the interactions that take place throughout the course of the mathematics lesson. While there was not a significant difference in the type of interaction and the modality of instruction, there was a significant difference in the type of interaction enacted and the modality of instruction.more » « less
-
Hwang, Gwo-Jen; Xie, Haoran; Wah, Benjamin; Gasevic, Dragan (Ed.)Classroom videos are a common source of data for educational researchers studying classroom interactions as well as a resource for teacher education and professional development. Over the last several decades emerging technologies have been applied to classroom videos to record, transcribe, and analyze classroom interactions. With the rise of machine learning, we report on the development and validation of neural networks to classify instructional activities using video signals, without analyzing speech or audio features, from a large corpus of nearly 250 h of classroom videos from elementary mathematics and English language arts instruction. Results indicated that the neural networks performed fairly-well in detecting instructional activities, at diverse levels of complexity, as compared to human raters. For instance, one neural network achieved over 80% accuracy in detecting four common activity types: whole class activity, small group activity, individual activity, and transition. An issue that was not addressed in this study was whether the fine-grained and agnostic instructional activities detected by the neural networks could scale up to supply information about features of instructional quality. Future applications of these neural networks may enable more efficient cataloguing and analysis of classroom videos at scale and the generation of fine-grained data about the classroom environment to inform potential implications for teaching and learning.more » « less
-
The construct of mathematical knowledge for teaching (MKT) has transformed research and practice regarding the mathematical preparation of future teachers. However, the measures used to assess MKT are largely written tasks, which may fail to adequately represent the nature of content knowledge as it is used in instructional decision making. This preliminary report shares initial findings into one measure of MKT in practice – mathematical errors made during planning and enactment of mathematics instruction. We analyzed lesson plans and classroom video from prospective secondary mathematics teachers (PSTs)’ supervised field experiences in college algebra course. We found that there tended be more errors related to understanding of functions (especially logarithmic), but relatively few errors happened overall during instruction. Of the errors made during planning, the majority of these errors were issues of mathematical precision. Implications for the mathematical preparation of secondary PSTs, as well as research on MKT in practice, are discussed.more » « less
