An official website of the United States government
VR displays (HMDs) with embedded eye trackers could enable better teacher-guided VR applications since eye tracking could provide insights into student’s activities and behavior patterns. We present several techniques to visualize eye-gaze data of the students to help a teacher gauge student attention level. A teacher could then better guide students to focus on the object of interest in the VR environment if their attention drifts and they get distracted or confused.
more »
« less
Instructional Activity Recognition Using A Transformer Network with Multi-Semantic Attention
Instructional activity recognition is an analytical tool for the observation of classroom education. One of the primary challenges in this domain is dealing with the intri- cate and heterogeneous interactions between teachers, students, and instructional objects. To address these complex dynamics, we present an innovative activity recognition pipeline designed explicitly for instructional videos, leveraging a multi-semantic attention mechanism. Our novel pipeline uses a transformer network that incorporates several types of instructional seman- tic attention, including teacher-to-students, students-to-students, teacher-to-object, and students-to-object relationships. This com- prehensive approach allows us to classify various interactive activity labels effectively. The effectiveness of our proposed algo- rithm is demonstrated through its evaluation on our annotated instructional activity dataset.
more »
« less
- PAR ID:
- 10523763
- Editor(s):
- Korban, Matthew; Acton, Scott T; Youngs, Peter; Foster, Jonathan
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 979-8-3503-6011-0
- Page Range / eLocation ID:
- 113 to 116
- Subject(s) / Keyword(s):
- Not applicable
- Format(s):
- Medium: X
- Location:
- Santa Fe, NM, USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Teachers' efforts to support students, both academically and socially, can play a role in how high school students productively engage with mathematics in the moment. To examine the connection between teacher support and student engagement, we conducted an exploratory mixed-methods study combining data from 20 high school classroom observations with student self-reports taken during the observed activity. Our findings indicate that when teachers provide academic support to their students during a lesson, they are also likely to provide social support. Higher teacher support of both kinds correlates with higher student self-efficacy, as well as social and cognitive engagement. Investigating relationships between observations of teaching and students' self-reports of engagement in-the-moment is a potentially revealing approach for uncovering engaging instructional strategies in secondary mathematics classrooms.more » « less
-
With the growing prevalence of AI, the need for K-12 AI education is becoming more crucial, which is prompting active research in developing engaging and age-appropriate AI learning activities. Efforts are underway, such as those by the AI4K12 initiative, to establish guidelines for organizing K- 12 AI education; however, effective instructional resources are needed by educators. In this paper, we describe our work to design, develop, and implement an unplugged activity centered on facial recognition technology for middle school students. Facial recognition is integrated into a wide range of applications throughout daily life, which makes it a familiar and engaging tool for students and an effective medium for conveying AI concepts. Our unplugged activity, “Guess Whose Face,” is designed as a board game that focuses on Representation and Reasoning from AI4K12’s 5 Big Ideas in AI. The game is crafted to enable students to develop AI competencies naturally through physical interaction. In the game, one student uses tracing paper to extract facial features from a familiar face shown on a card, such as a cartoon character or celebrity, and then other students try to guess the identity of the hidden face. We discuss details of the game, its iterative refinement, and initial findings from piloting the activity during a summer camp for rural middle school students.more » « less
-
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
-
Recent educational reforms conceptualize science classrooms as spaces where students engage in Science-as-Practice to develop deep understandings of scientific phenomena. When students engage in Science-as-Practice they are constructing explanations, arguing from evidence, and evaluating and communicating information to develop scientific knowledge (NGSS Lead States, 2013). This process of learning requires a focus on productive science talk in which students grapple with and socially negotiate their ideas (Kelly, 2014) through interactions involving talk, joint attention, and shared activity aimed at building, negotiating, and refining new understandings of phenomena and relevant science concepts (Ford, 2015; Michaels & O’Connor, 2012). Productive talk requires the ‘nimble’ involvement of the teacher to help students productively contribute their ideas to the class and use them as resources to drive instructional activities supporting the development and refinement of more sophisticated scientific understandings (Christodoulou & Osborne, 2014; González‐Howard & McNeill, 2020).more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Conference Paper:
- https://doi.org/10.1109/SSIAI59505.2024.10508634
