Once More, With Feeling: Measuring Emotion of Acting Performances in Contemporary American Film

TL;DR

Applying speech emotion recognition models and a variationist sociolinguistic analytical framework to a corpus of popular, contemporary American film, narrative structure, diachronic shifts, and genre- and dialogue-based constraints located in spoken performances are found.

Abstract

Narrative film is a composition of writing, cinematography, editing, and performance. While much computational work has focused on the writing or visual style in film, we conduct in this paper a computational exploration of acting performance. Applying speech emotion recognition models and a variationist sociolinguistic analytical framework to a corpus of popular, contemporary American film, we find narrative structure, diachronic shifts, and genre- and dialogue-based constraints located in spoken performances.

Figures (3)

• Figure 1: Emotionality increases, but specific emotions show non-linear trajectories over narrative time (95% bootstrap confidence interval).
• Figure 2: Emotionality is higher in older films (95% bootstrap confidence interval).
• Figure 3: Relative emotional range for different film genres (95% bootstrap confidence intervals).