Joint Estimation and Analysis of Risk Behavior Ratings in Movie Scripts

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 4780–4790, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 4780 Joint Estimation and Analysis of Risk Behavior Ratings in Movie Scripts Victor R Martinez University of Southern California Los Angeles, CA victorrm@usc.edu Krishna Somandepalli University of Southern California Los Angeles, CA Yalda T. Uhls University of California, Los Angeles Los Angeles, CA Shrikanth Narayanan University of Southern California Los Angeles, CA shri@sipi.usc.edu Abstract Exposure to violent, sexual, or substance- abuse content in media increases the will- ingness of children and adolescents to imi- tate similar behaviors. Computational methods that identify portrayals of risk behaviors from audio-visual cues are limited in their applica- bility to films in post-production, where modi- fications might be prohibitively expensive. To address this limitation, we propose a model that estimates content ratings based on the lan- guage use in movie scripts, making our so- lution available at the earlier stages of cre- ative production. Our model significantly im- proves the state-of-the-art by adapting novel techniques to learn better movie representa- tions from the semantic and sentiment aspects of a character’s language use, and by leverag- ing the co-occurrence of risk behaviors, fol- lowing a multi-task approach. Additionally, we show how this approach can be useful to learn novel insights on the joint portrayal of these behaviors, and on the subtleties that film- makers may otherwise not pick up on. 1 Introduction In one of the longest running movie franchises in history, fictional British Secret Service agent James Bond is more often than not portrayed as an extremely charming gentleman, a cold-blooded killer, a smoker, and a severe alcoholic (Wilson et al., 2018). This is not a unique character trait, as other critically acclaimed films—such as, The Exorcist (Friedkin, 1973), Pulp Fiction (Tarantino, 1994), and A Clockwork Orange (Kubrick, 1972)— follow narratives where the main characters engage in a similar collection of risk behaviors. The por- trayals of these risk behaviors typically include acts of violence, sexual and substance-abusive be- haviors in scenes of fighting, bloodshed, gunplay; intercourse and nudity; and alcohol, smoking and drug use, respectively. While these tend to attract audiences (Barranco et al., 2017) and facilitate a movie’s global market reach (Sparks et al., 2005), they have long sparked concerns about the potential side effects of repeated exposure. Particularly, in the case of at-risk populations, such as children and adolescents, where this exposure has been linked to increased risk for engaging in violence (Ander- son and Bushman, 2001; Bushman and Huesmann, 2001), smoke and alcohol consumption (Sargent et al., 2005; Dal Cin et al., 2008), and earlier sexual initiation (Brown et al., 2006). Although various automated tools have been designed to recognize risk behaviors portrayals (e.g., (Chen et al., 2011; Liu et al., 2008)), many rely on cinematic principles from film theory such as illumination, rapid shot transitions or musical score selection (Brezeale and Cook, 2008). This limits their practical impact to an almost-final edi- tion of the content, specifically where …

Content truncated to 500 words