Abstract
dc:description.abstractThis thesis presents a comprehensive multimodal film–music dataset assembled to support large-scale studies of how music, image, and dialogue interact in cinema. Drawing on a carefully stratified sample of feature films spanning multiple genres, countries, and decades, we describe an open, end-to-end workflow for extracting and aligning musical passages with video frames, semantic labels, and subtitle transcripts. We validate our extraction and annotation procedures through human evaluation of cue detection and music-feature recognition. Exploratory analyses illustrate how orchestration varies by genre, how soundtrack emotion tracks narrate mood, and how the presence of dialogue shapes musical impact. By sharing both the data and the methods, this work lays a foundation for reproducible, cross-modal research in computational musicology, affective computing, and film studies.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Music
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Jafari, Farshad
- Advisor dc:contributor.advisor
-
- Arthur, Claire
- Committee members dc:contributor.committeemember
-
- Lerch, Alexander
- Condit-Schultz, Nat
Subjects
dc:subject × 1Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/82045