Toward Automated Feedback on Teacher Discourse to Enhance Teacher Learning. Research supports coaching as critical for effective teacher professional development. A key element of coaching is observing teachers in classrooms implementing newly trained skills. Unfortunately, one of the obstacles to providing coaching to teachers is the cost of delivering the service. Educators are on the lookout for any innovations that promise to reduce this cost of coaching while sustaining the impact of coaching. Research has found the use of video and remote viewing coaching to show much promise (Scheeler, Congdon, & Stansbery, 2010; Suhrheinrich, 2017). This study examines the use of an automated recording of high-quality audio using speech recognition and machine learning to develop teacher-generalizable computer-scored estimates of crucial features of teacher’s performance.
The study found that computerized models were moderately accurate compared to human coders and that speech recognition errors did not influence performance. The authors conclude that teacher discourse can be recorded and analyzed for timely feedback. The next step is to incorporate the automatic models into an interactive visualization tool that will provide teachers with objective feedback on student instruction quality.
Citation: Darling-Hammond, L., Hyler, M. E., & Gardner, M. (2017). Effective teacher professional development.
Link: https://dl.acm.org/doi/abs/10.1145/3313831.3376418 (This paper may also be requested on Researchgate)