Classroom sound can be used to classify teaching practices in college science courses

作者：Melinda T. Owens, Shannon B. Seidel, Mike Wong, Travis E. Bejines, Susanne Lietz, Joseph R. Perez, Shangheng Sit, Zahur-Saleh Subedar, Gigi N. Acker, Susan F. Akana, Brad Balukjian, Hilary P. Benton, J. R. Blair, Segal M. Boaz, Katharyn E. Boyer, Jason Bram, Laura W. Burrus, Dana T. Byrd, Natalia Caporale, Edward J. Carpenter, Yee-Hung M. Chan, Lily Chen, Amy Chovnick, Diana S. Chu, Bryan K. Clarkson, Sara Cooper, Catherine Creech, Karen D. Crow, José R. de la Torre, Wilfred F. Denetclaw, Kathleen E. Duncan, Amy S. Edwards, Karen L. Erickson, Megumi Fusé, Joseph J. Gorga, Brinda Govindan, L. Jeanette Green, Paul Z. Hankamp, Holly E. Harris, Zheng‐Hui He, Stephen B. Ingalls, Peter Ingmire, J. Rebecca Jacobs, Mark Kamakea, Rhea R. Kimpo, Jonathan D. Knight, Sara K. Krause, Lori E. Krueger, Terrye L. Light, Lance Lund, Leticia Márquez-Magaña, Briana K. McCarthy, Linda J. McPheron, Vanessa C. Miller‐Sims, Christopher A. Moffatt, Pamela C. Muick, Paul H. Nagami, Gloria Nusse, Kristine M. Okimura, Sally G. Pasion, Robert Patterson, Pleuni S. Pennings, Blake Riggs, Joseph M. Romeo, Scott William Roy, Tatiane Russo‐Tait, Lisa M. Schultheis, Lakshmikanta Sengupta, Rachel Small, Greg S. Spicer, Jonathon H. Stillman, Andrea Swei, Jennifer M. Wade, Steven B. Waters, Steven L. Weinstein, Julia K. Willsie, Diana W. Wright, Colin Harrison, Loretta Kelley, Gloriana Trujillo, Carmen R. Domingo, Jeffrey N. Schinske, Kimberly D. Tanner · 发表于：Proceedings of the National Academy of Sciences · 年份：2017 · DOI：10.1073/pnas.1618693114 · 被引用次数：90 · 研究领域：Innovative Teaching Methods、Experimental Learning in Engineering、Visual and Cognitive Learning Processes

Active-learning pedagogies have been repeatedly demonstrated to produce superior learning gains with large effect sizes compared with lecture-based pedagogies. Shifting large numbers of college science, technology, engineering, and mathematics (STEM) faculty to include any active learning in their teaching may retain and more effectively educate far more students than having a few faculty completely transform their teaching, but the extent to which STEM faculty are changing their teaching methods is unclear. Here, we describe the development and application of the machine-learning-derived algorithm Decibel Analysis for Research in Teaching (DART), which can analyze thousands of hours of STEM course audio recordings quickly, with minimal costs, and without need for human observers. DART analyzes the volume and variance of classroom recordings to predict the quantity of time spent on single voice (e.g., lecture), multiple voice (e.g., pair discussion), and no voice (e.g., clicker question thinking) activities. Applying DART to 1,486 recordings of class sessions from 67 courses, a total of 1,720 h of audio, revealed varied patterns of lecture (single voice) and nonlecture activity (multiple and no voice) use. We also found that there was significantly more use of multiple and no voice strategies in courses for STEM majors compared with courses for non-STEM majors, indicating that DART can be used to compare teaching strategies in different types of courses. Therefore, DART has t...