A Dynamic Model of Speech for the Social Sciences

98 Pages Posted: 10 Dec 2019 Last revised: 1 Sep 2020

See all articles by Dean Knox

Dean Knox

Princeton University

Christopher Lucas

Washington University in St. Louis

Date Written: November 22, 2019


Speech and dialogue are the heart of politics: Nearly every political institution in the world involves verbal communication. Yet vast literatures on political communication focus almost exclusively on what words were spoken, entirely ignoring how they were delivered---auditory cues that convey emotion, signal positions, and establish reputation. We develop a model that opens this untapped information to principled statistical inquiry: the model of audio and speech structure (MASS). Our approach models political speech as a stochastic process shaped by fixed and time-varying covariates, including the history of the conversation itself. In an application to Supreme Court oral arguments, we demonstrate how vocal delivery signals crucial information---skepticism of legal arguments---that is indecipherable to text models. Results show that justices do not use questioning to strategically manipulate their peers, but rather engage in genuine fact-finding efforts. Our easy-to-use R package, speech, implements the model and many more tools for audio analysis.

Keywords: Speech dynamics; Signal processing; Conversation; Emotion; Hidden Markov model; Latent process

Suggested Citation

Knox, Dean and Lucas, Christopher, A Dynamic Model of Speech for the Social Sciences (November 22, 2019). Available at SSRN: https://ssrn.com/abstract=3490753 or http://dx.doi.org/10.2139/ssrn.3490753

Dean Knox (Contact Author)

Princeton University ( email )

001 Fisher Hall
Princeton, NJ 08544
United States

Christopher Lucas

Washington University in St. Louis ( email )

One Brookings Drive
Campus Box 1208
Saint Louis, MO MO 63130-4899
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics