Search for: All records

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. 

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. 

Argumentation is a practice that spans STEM disciplines and is an explicit goal for K12 students in reform-based standards documents. The purpose of this study was to investigate the applicability of Douglas Walton’s theoretical model for describing the types of argument dialogue encountered in elementary classrooms focused on learning concepts in science, mathematics, and computer coding. We examined two elementary teachers’ STEM classrooms to explore the types of argument dialogue that were evident. We found evidence of six types of dialogues: persuasion, negotiation, information-seeking, deliberation, inquiry, and discovery based on Walton’s model. Our findings demonstrate the applicability of Walton’s types of argument dialogue to argumentation in elementary STEM contexts. Even though our work takes place in the United States with teachers of children in grades 3-5 (ages 8-10 years), we believe our approach is applicable to other dialogues found in K12 STEM education. We postulate that students having opportunities to engage in arguments with a diverse range of goals (e.g., to prove a hypothesis, to persuade, or to exchange information) is important for their development in learning how to argue in STEM. 

Current education reforms call for engaging students in learning science, technology, engineering, and mathematics (STEM) in an integrative way. This critical case study of one fourth grade teacher investigated the use of educational robots (ER) not only for teaching coding, but as an instructional support in teaching mathematical concepts. To support teachers in teaching coding in an integrative and logical manner, our team developed the Collective Argumentation Learning and Coding (CALC) approach. The CALC approach consists of three elements: choice of task, coding content, and teacher support for argumentation. After a cohort of elementary teachers completed a professional development course, we followed them into their classrooms to support and document implementation of the CALC approach. Data for this case consisted of video recordings of two lessons, a Pre-interview, and Post-interview after each lesson. Research questions included: How does an elementary teacher use the CALC approach (integrative STEM approach) to teach mathematics concepts with ER? What are the teacher’s perspectives towards teaching mathematics with ER using an integrative STEM approach? Results from this critical case provide evidence that teachers can successfully integrate ER into the mathematics curriculum without losing coherence of mathematics topics and while remaining sensitive to students’ needs.