A Graph-Learning Approach for Detecting Moral Conflict in Movie Scripts
Moral conflict is central to appealing narratives, but no methodology exists for computationally extracting moral conflict from narratives at scale. In this article, we present an approach combining tools from social network analysis and natural language processing with recent theoretical advancemen...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cogitatio
2020-08-01
|
| Series: | Media and Communication |
| Subjects: | |
| Online Access: | https://www.cogitatiopress.com/mediaandcommunication/article/view/3155 |
| _version_ | 1818010828504301568 |
|---|---|
| author | Frederic René Hopp Jacob Taylor Fisher René Weber |
| author_facet | Frederic René Hopp Jacob Taylor Fisher René Weber |
| author_sort | Frederic René Hopp |
| collection | DOAJ |
| description | Moral conflict is central to appealing narratives, but no methodology exists for computationally extracting moral conflict from narratives at scale. In this article, we present an approach combining tools from social network analysis 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 894 movie scripts encompassing 82,195 scenes, 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 conflict 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. |
| first_indexed | 2024-04-14T06:00:36Z |
| format | Article |
| id | doaj.art-1fc9c99ee68b4962998a632d53b22d2e |
| institution | Directory Open Access Journal |
| issn | 2183-2439 |
| language | English |
| last_indexed | 2024-04-14T06:00:36Z |
| publishDate | 2020-08-01 |
| publisher | Cogitatio |
| record_format | Article |
| series | Media and Communication |
| spelling | doaj.art-1fc9c99ee68b4962998a632d53b22d2e2022-12-22T02:08:47ZengCogitatioMedia and Communication2183-24392020-08-018316417910.17645/mac.v8i3.31551580A Graph-Learning Approach for Detecting Moral Conflict in Movie ScriptsFrederic René Hopp0Jacob Taylor Fisher1René Weber2Media Neuroscience Lab, Department of Communication, University of California Santa Barbara, USAMedia Neuroscience Lab, Department of Communication, University of California Santa Barbara, USAMedia Neuroscience Lab, Department of Communication, University of California Santa Barbara, USAMoral conflict is central to appealing narratives, but no methodology exists for computationally extracting moral conflict from narratives at scale. In this article, we present an approach combining tools from social network analysis 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 894 movie scripts encompassing 82,195 scenes, 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 conflict 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.https://www.cogitatiopress.com/mediaandcommunication/article/view/3155computational narratologyentertainmentemfdgraph learningmimemoral conflictmovie scriptsnetwork science |
| spellingShingle | Frederic René Hopp Jacob Taylor Fisher René Weber A Graph-Learning Approach for Detecting Moral Conflict in Movie Scripts Media and Communication computational narratology entertainment emfd graph learning mime moral conflict movie scripts network science |
| title | A Graph-Learning Approach for Detecting Moral Conflict in Movie Scripts |
| title_full | A Graph-Learning Approach for Detecting Moral Conflict in Movie Scripts |
| title_fullStr | A Graph-Learning Approach for Detecting Moral Conflict in Movie Scripts |
| title_full_unstemmed | A Graph-Learning Approach for Detecting Moral Conflict in Movie Scripts |
| title_short | A Graph-Learning Approach for Detecting Moral Conflict in Movie Scripts |
| title_sort | graph learning approach for detecting moral conflict in movie scripts |
| topic | computational narratology entertainment emfd graph learning mime moral conflict movie scripts network science |
| url | https://www.cogitatiopress.com/mediaandcommunication/article/view/3155 |
| work_keys_str_mv | AT fredericrenehopp agraphlearningapproachfordetectingmoralconflictinmoviescripts AT jacobtaylorfisher agraphlearningapproachfordetectingmoralconflictinmoviescripts AT reneweber agraphlearningapproachfordetectingmoralconflictinmoviescripts AT fredericrenehopp graphlearningapproachfordetectingmoralconflictinmoviescripts AT jacobtaylorfisher graphlearningapproachfordetectingmoralconflictinmoviescripts AT reneweber graphlearningapproachfordetectingmoralconflictinmoviescripts |