Abstract
Traditional methods of analyzing film narrative structure typically involve qualitative analyses of script and film elements as well as quantitative assessments of editing patterns. These approaches are limited by scalability and efficiency due to the extensive manual human labor required, making them impractical for analyzing large datasets. This paper examines how machine learning techniques can be leveraged to classify film narrative structures in a more scalable and efficient manner, particularly when dealing with extensive collections of films. To address the limitations of traditional methods, two main approaches are proposed. The first approach utilizes natural language processing (NLP) to perform script sentiment analysis and identify the hidden emotional structures across a large body of film scripts. The second approach uses computer vision techniques to detect editing elements such as transitions and shot duration patterns, which are then analyzed to uncover the underlying narrative structures within a corpus of films. Each approach has its strengths and limitations depending on the availability of samples and practical considerations. These machine learning techniques offer a scalable and efficient way to analyze narrative structures, enabling film scholars to uncover hidden complex patterns within large datasets of films. Practically, these techniques can also assist filmmakers in fine-tuning their work, ensuring that the pacing and emotional impact align with their creative vision. Overall, this integration of technology into film studies and production enhances traditional methods of film study and helps filmmakers make more informed decisions.
Author Information
Nuttanai Lertpreechapakdee, Chulalongkorn University, Thailand
Tatri Taiphapoon, Chulalongkorn University, Thailand
Sukree Sinthupinyo, Chulalongkorn University, Thailand
Paper Information
Conference: MediAsia2024
Stream: Film Criticism and Theory
This paper is part of the MediAsia2024 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window
To cite this article:
Lertpreechapakdee N., Taiphapoon T., & Sinthupinyo S. (2024) Toward Automating the Classification of Films’ Narrative Structures ISSN: 2186-5906 – The Asian Conference on Media, Communication & Film 2024: Official Conference Proceedings (pp. 197-207) https://doi.org/10.22492/issn.2186-5906.2024.17
To link to this article: https://doi.org/10.22492/issn.2186-5906.2024.17
Comments
Powered by WP LinkPress