Automated Classroom Observation: Can Neural Networks Estimate PLATO (Protocol for Language Arts Teaching Observation) Classroom Management and Instructional Domains? (Poster 41)

• In Event: Thursday Poster Session 10:50 am
  In Poster Session: Technology, Instruction, Cognition, and Learning SIG Poster Session

Abstract

Despite the promise of different neural networks to engage in summative assessment of instructional videos, there has been little research in this area. This study is designed to address this shortcoming in the research literature. We utilized 250 hours of videos of elementary mathematics and ELA lessons that had previously been rated by individuals trained in the use of the Protocol for Language Arts Teaching Observation (PLATO) instrument (Grossman et al., 2014). In particular, we examined correlations between PLATO classroom management and instructional domains and (a) human annotations and (b) neural network classifications of individual features of instruction and combinations of aspects of instruction in the observed lessons.

Authors

• Peter A. Youngs, University of Virginia

• Kayla Michelle Reist, University of Virginia

• James Drimalla, University of Virginia

• Pawan Gupta, University of Virginia

• Jonathan K. Foster, University at Albany - SUNY