New PNAS Publication on an Algorithm that Uses Sound to Identify Teaching Practices in College Classrooms!

Detecting active learning in college classrooms 

Researchers designed an algorithm that uses sound to identify teaching practices in college classrooms. Previous studies show that classes with active learning, when students learn through talking and problem solving, result in higher learning gains and student retention than lecture-only classes. Hundreds of millions of dollars have been invested to shift science, technology, engineering, and math (STEM) college courses from the common lecture-based teaching style to more active learning. Kimberly Tanner and colleagues designed Decibel Analysis for Research in Teaching (DART), a machine-learning algorithm that rapidly analyzes classroom audio recordings, to quantify the frequency of different teaching practices in a classroom. For 1,486 recordings from 67 college courses across 21 community colleges and universities, DART distinguished the amount of classroom time spent with no voices or thinking/writing time, one voice or lecture/question-and-answer time, and multiple voices or discussion time. DART identified teaching styles with an approximately 90% accuracy rate and worked well in both small and large classes. The amount of time spent on active learning activities—both no voices and multiple voices activities—was higher for courses for STEM majors than courses for non-STEM majors, and 88% of courses analyzed here used active learning in at least half of class sessions. Given its efficiency, DART makes regular, systematic analyses of the use of active learning in classrooms possible for individual instructors, departments, institutions, and researchers, according to the authors.

For more information, click here