For decades, the field of film production has been driven by marketability, and it has relied on gut feelings and subjectivity to produce feature films. The analysis of the relationship between a screenplay’s narrative and a film’s success has been widely overlooked due to the challenges involved in data acquisition and complexity. This study investigates the predictive power of narrative structure on film success and aims to build evidence for hypothesized narrative principles. The results suggest that narrative structural elements exhibit moderate predictive power, with strong support for the alignment of the 2nd act crucial moments and the 2nd act main tension moments. Additionally, the data supports empathy moments clustering towards the beginning of the first act. The predictive analysis was conducted using a logistic regression model fitted on augmented data split into training and testing sets. Inferential analysis was performed through Bayesian logistic regression, calculating causal estimates and 80% credible intervals derived from four chains with 10,000 iterations, including a 5,000 iteration burn-in period to ensure convergence. Overall, the findings reveal that narrative principles are worth further investigation, with the potential to develop practical tools for enhancing narrative effectiveness.
","abstract_html":"<p>For decades, the field of film production has been driven by marketability, and it has relied on gut feelings and subjectivity to produce feature films. The analysis of the relationship between a screenplay’s narrative and a film’s success has been widely overlooked due to the challenges involved in data acquisition and complexity. This study investigates the predictive power of narrative structure on film success and aims to build evidence for hypothesized narrative principles. The results suggest that narrative structural elements exhibit moderate predictive power, with strong support for the alignment of the 2nd act crucial moments and the 2nd act main tension moments. Additionally, the data supports empathy moments clustering towards the beginning of the first act. The predictive analysis was conducted using a logistic regression model fitted on augmented data split into training and testing sets. Inferential analysis was performed through Bayesian logistic regression, calculating causal estimates and 80% credible intervals derived from four chains with 10,000 iterations, including a 5,000 iteration burn-in period to ensure convergence. Overall, the findings reveal that narrative principles are worth further investigation, with the potential to develop practical tools for enhancing narrative effectiveness.</p>","abstract_has_math":false,"creators":["Trombley, Arisa T"],"institution":null,"degree_name":null,"degree_level":"Thesis","degree_discipline":"Electrical Engineering and Computer Science","degree_department":null,"school":null,"contributors":["Jonathan Humphreys","Erik Linstead","Chelsea Parlett"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05-01T07:00:00Z","date_published":"2025-05-01T07:00:00Z","updated_at":"2026-07-24T01:38:43Z","subjects":["narrative principles","Bayesian","causal inference","Data Science","Film Production","Screenwriting"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.chapman.edu/eecs_theses/8","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Jonathan Humphreys","Erik Linstead","Chelsea Parlett"]},{"key":"dc:creator","label":"Author","values":["Trombley, Arisa T"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-11-18T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering and Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["narrative principles","Bayesian","causal inference","Data Science","Film Production","Screenwriting"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.chapman.edu/eecs_theses/8"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["For decades, the field of film production has been driven by marketability, and it has relied on gut feelings and subjectivity to produce feature films. The analysis of the relationship between a screenplay’s narrative and a film’s success has been widely overlooked due to the challenges involved in data acquisition and complexity. This study investigates the predictive power of narrative structure on film success and aims to build evidence for hypothesized narrative principles. The results suggest that narrative structural elements exhibit moderate predictive power, with strong support for the alignment of the 2nd act crucial moments and the 2nd act main tension moments. Additionally, the data supports empathy moments clustering towards the beginning of the first act. The predictive analysis was conducted using a logistic regression model fitted on augmented data split into training and testing sets. Inferential analysis was performed through Bayesian logistic regression, calculating causal estimates and 80% credible intervals derived from four chains with 10,000 iterations, including a 5,000 iteration burn-in period to ensure convergence. Overall, the findings reveal that narrative principles are worth further investigation, with the potential to develop practical tools for enhancing narrative effectiveness.
"]},{"key":"dc:source","label":"Dc Source","values":["A. T. Trombley, \"A Narrative-Focused Machine Learning Approach to Predicting Feature Film Success,\" M. S. thesis, Chapman University, Orange, CA, 2025. https://doi.org/10.36837/chapman.000681"]},{"key":"dc:title","label":"Title","values":["A Narrative-Focused Machine Learning Approach to Predicting Feature Film Success"]}]}],"canonical_facts":{"dc:contributor":["Jonathan Humphreys","Erik Linstead","Chelsea Parlett"],"dc:creator":["Trombley, Arisa T"],"dc:date.available":["2025-11-18T08:00:00Z"],"dc:description.abstract":["For decades, the field of film production has been driven by marketability, and it has relied on gut feelings and subjectivity to produce feature films. The analysis of the relationship between a screenplay’s narrative and a film’s success has been widely overlooked due to the challenges involved in data acquisition and complexity. This study investigates the predictive power of narrative structure on film success and aims to build evidence for hypothesized narrative principles. The results suggest that narrative structural elements exhibit moderate predictive power, with strong support for the alignment of the 2nd act crucial moments and the 2nd act main tension moments. Additionally, the data supports empathy moments clustering towards the beginning of the first act. The predictive analysis was conducted using a logistic regression model fitted on augmented data split into training and testing sets. Inferential analysis was performed through Bayesian logistic regression, calculating causal estimates and 80% credible intervals derived from four chains with 10,000 iterations, including a 5,000 iteration burn-in period to ensure convergence. Overall, the findings reveal that narrative principles are worth further investigation, with the potential to develop practical tools for enhancing narrative effectiveness.
"],"dc:identifier":["https://digitalcommons.chapman.edu/eecs_theses/8"],"dc:source":["A. T. Trombley, \"A Narrative-Focused Machine Learning Approach to Predicting Feature Film Success,\" M. S. thesis, Chapman University, Orange, CA, 2025. https://doi.org/10.36837/chapman.000681"],"dc:subject":["narrative principles","Bayesian","causal inference","Data Science","Film Production","Screenwriting"],"dc:title":["A Narrative-Focused Machine Learning Approach to Predicting Feature Film Success"],"thesis:degree_discipline":["Electrical Engineering and Computer Science"],"thesis:degree_level":["Thesis"]},"updated_at":"2026-07-24T01:38:43Z"}