A Graph-Learning Approach for Detecting Moral Conflicts in Movie Scripts
Date created: | Last Updated:
: DOI | ARK
Creating DOI. Please wait...
Description: Moral conflict is central to appealing narratives, but no methodology exists for computationally extracting moral conflict from narratives at scale. In this project, we present an approach combining tools from network science and natural language processing with recent theoretical advancements in the Model of Intuitive Morality and Exemplars. This approach considers narratives in terms of a network of dynamically evolving relationships between characters. We apply this method in order to analyze movie scripts, showing that scenes containing moral conflict between central characters can be identified using changes in connectivity patterns between network modules. Furthermore, we derive computational models for standardizing moral conflict measurements. Our results suggest that this method can accurately extract moral conflicts from a diverse collection of movie scripts. We provide a theoretical integration of our method into the larger milieu of storytelling and entertainment research, illuminating future research trajectories at the intersection of computational communication research and media psychology. This project is dual-licensed under GNU GENERAL PUBLIC LICENSE 3.0, which permits the non-commercial use, distribution, and modification of the herein utilized code. Any commercial use of the herein described methods, code, and data requires an application: https://docs.google.com/forms/d/e/1FAIpQLSc5zS8YK1b_rD6zAEZFfKZTvsqwRElgst5_YFaUwOO_FR5SRg/viewform