Assessing the Impact of Active Learning Strategies in Large-Enrollment Courses

Active learning strategies have gained prominence in higher education for their potential to enhance student engagement and learning outcomes. However, assessing their effectiveness in large enrollment courses remains challenging. This study examines the impact of active learning components in two large enrollment psychology courses and demonstrates the application of advanced Natural Language Processing (NLP) techniques in analyzing student feedback comments in course evaluations. We compared traditional lecture-based formats with active learning approaches in two large courses in Psychology (A Survey of the Neural Basis of Behavior and Introduction to Cognition). Student feedback was analyzed using zero-shot classification via Facebook's BART Large Language Model, categorizing responses into four dimensions: learning experience, engagement, perceived learning, and excitement about content. Results showed significant improvements in all dimensions for both courses under the active learning format, with particularly strong effects on learning experience and engagement. The Introduction to Cognition course showed a non-significant trend in increased excitement about content. The innovative NLP approach provided nuanced insights into student perceptions, overcoming limitations of traditional course evaluations. This study contributes to the growing body of evidence supporting active learning in large classes and introduces a scalable, efficient method for assessing pedagogical innovations in higher education.