Gender and Tone in Recorded Economics Presentations: Audio Analysis with Machine Learning
48 Pages Posted: 3 Jan 2023 Last revised: 6 Sep 2023
Date Written: January 1, 2023
Abstract
This paper measures seminar dynamics using a replicable, scalable, machine-learning approach and finds a gender-tone gap in economics presentations. We train a deep convolutional neural network to impute labels for gender, age, and tone-of-voice. We apply this to recorded presentations from the 2022 NBER Summer Institute to measure tone at a high frequency, which allows us to provide novel results on how economists interact with each other in talks. We find that female economists are more likely to speak in a positive tone and less likely to be spoken to in a positive tone, even by other women. We find that male economists are significantly more likely to sound angry or stern compared to female economists. Overall, we conclude that gender biases in economics presentations exist across fields and presentation formats.
Keywords: machine learning, audio analysis, gender, seminar dynamics, tone
JEL Classification: A1, C8, C45
Suggested Citation: Suggested Citation