Classification of Instructional Activities in Classroom Videos Using Neural Networks
Year: 2024
Type: book-chapter
Abstract: Classroom videos have become an integral part of classroom observation and instructional quality studies. Researchers encounter substantial financial and time-consuming costs gathering trained personnel to catalogue and analyze a large quantity (i.e., hundreds of hours) of classroom videos. In this chapter, we argue that deep-learning neural networks have potential to help with these tasks by detecting features of instruction in videos. We evaluated the performance of three neural networks in detecting instructional activities in classroom videos. The video dataset included a total of forty-six hours, which was evenly split between elementary mathematics and English language arts lesson recordings. Results showed that the three neural networks detected instructional activities with a moderate degree of accuracy. We discuss potential opportunities and challenges in automating classroom observations with neural networks for educational research and teaching practice.
Source: Oxford University Press eBooks
Authors: Jonathan K. Foster, Matthew Korban, Peter Youngs, Ginger S. Watson, Scott T. Acton
Language: English
Subfield: Education
Field: Social Sciences
Domain: Social Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W4404604719